https://gisj.sbu.ac.ir/ Iranian Journal of Remote Sensing and GIS en daily 1 Wed, 21 Jan 2026 00:00:00 +0330 Wed, 21 Jan 2026 00:00:00 +0330 https://gisj.sbu.ac.ir/article_104760.html Introduction: Human activities and climate change directly affect the earth's surface cover. In the northern part of the country, land use changes have emerged as a significant factor contributing to the destruction of vegetation in Hyrcanian forests. Unfortunately, this destruction has persisted over the past few decades due to human activities. Golestan province, known for its diverse climate and surface cover, has experienced noticeable changes in vegetation, illustrating the impacts of these activities. Therefore, it is crucial to monitor the dynamics of vegetation in order to gain a better understanding of how vegetation respond to human pressures. This knowledge is essential for preserving the Hyrcanian forests.Materials and Methods: The investigation and monitoring of vegetation cover in Golestan province involved the use of the Normalized Difference Vegetation Index (NDVI). To analyze vegetation trends over a 20-year period, 16-day combined MODIS-NDVI time series data (MOD13Q1) with a spatial resolution of 250 meters, were utilized. The research began with the acquisition of raw NDVI images in HDF format from the NASA website. These 920 images, from the 16-day time series, were then analyzed statistically. To standardize the images and facilitate further analysis, they were converted into 460 images through mosaicing and scaling between -1 and +1. The evaluation of serial trends was performed in IDRISI TerrSet software, where the images underwent a preprocessing step to remove seasonal anomalies. The changes in vegetation activity and their significance were subsequently analyzed using the non-parametric Mann-Kendall method.Results and Discussion: The results indicate that 20% of the studied area experienced a decrease in vegetation, while 80% exhibited an increase. Out of these, 5% had a significant decrease, and 50% showed a significant increase in vegetation, while the remaining had no discernible trend. Over the past 20 years, a total of 4088 square kilometers of vegetation has been lost. To analyze the impact of human activities on these changes, location maps of cities and main routes were utilized. The findings revealed that the northern plains of Golestan exhibited a greater reduction in vegetation due to easier land access for human activities, changes in land use, and urban development. The cities of Kordkoy, Bandar Gaz, Aqqala, Gorgan, Azadshahr, and Ramian experienced the most significant increase in vegetation cover, whereas the cities of Bandar Turkman, Gonbadkavoos, Minoodasht, and Kalaleh witnessed the most significant decrease. The main routes leading to Golestan province, including Gorgan-Bujnoord, Gorgan-Sari, Azadshahr-Semnan, Incheh Brun West Road, and Incheh Brun East Road, all showed a decline in vegetation in their vicinity. Due to the significant climatic diversity in Golestan province, surface cover changes were examined at specific locations where a substantial reduction in vegetation cover was expected.Conclusion: Based on the research conducted from 2001 to 2020, it can be concluded that the highlands of Golestan province, particularly the western highlands, have witnessed an increase in vegetation. This phenomenon is believed to be correlated with the rise in temperature resulting from global warming, which has created more favorable conditions for plant growth in these highland areas. In contrast, low-altitude regions such as plains, coastal areas, lower elevations, and especially areas surrounding cities and roads, have experienced a decline in vegetation cover. This decline can be attributed to human activities, including changes in land use and urbanization in the northern plains of Golestan. These changes signify the loss of extensive vegetation and the exacerbation of detrimental impacts from both human activities and natural factors. Although the reduction in vegetation in the highlands has been relatively slower compared to the lower regions, concerns arise regarding the destruction of vegetation in pristine forest areas. These developments highlight the urgent need for immediate attention and implementation of measures for sustainable management of natural resources and adaptation to climate change. https://gisj.sbu.ac.ir/article_104820.html Introduction: With the growth of urban populations, attention to urban safety and security has become one of the primary priorities for city managers and urban planners. Urban crises, especially in historical and deteriorated fabrics, can pose serious threats to the safety and livability of neighborhoods and lead to widespread destruction. Due to their specific characteristics—such as physical deterioration, high population density, lack of adequate infrastructure, and weak urban services—deteriorated urban fabrics are among the most vulnerable areas when facing urban crises like earthquakes, floods, and other natural or social disasters. In recent years, various studies and programs have been conducted to rehabilitate and renovate these areas and improve the quality of life for their residents. However, the focus on the livability of these fabrics in the face of urban crises and the use of futures studies for crisis prediction and management have received less attention. On the other hand, defining multipurpose spaces and their balanced distribution within neighborhoods, particularly in deteriorated fabrics with historical value, can contribute to improving the quality of life before a crisis and enhancing crisis management afterward.Materials and Methods: The lack of integration of future research with planning and crisis management is one of the gaps that this research examines how to improve crisis management conditions in the future by using future research techniques and spatial models, and fills this gap with innovation based on predictive analysis and possible scenarios. This research focuses on preserving the livability of deteriorated urban fabrics during urban crises using futures studies, specifically concentrating on the Imamzadeh Yahya neighborhood. It employs scenario writing to explore possible options for the future livability of this neighborhood. By analyzing livability criteria during crises using ArcGIS software and multi-criteria decision-making techniques, and leveraging CommunityVIZ Scenario360 software, the study examines the impact of variables across three different scenarios. Ultimately, the optimal scenario for creating multipurpose spaces is proposed.Results and Discussion: The findings reveal that selecting the optimal scenario and analyzing various layers emphasize the importance of open spaces, connectivity arteries, and vacant areas in the deteriorated urban fabric of the Imamzadeh Yahya neighborhood for urban crisis management. Furthermore, the research using CommunityVIZ Scenario 360 demonstrated that the northern and northwestern areas of the neighborhood are identified as suitable locations for defining multipurpose spaces, which can be effective in spatial enhancement and maintaining livability after a crisis. Additionally, the results indicate that low-cost and minimal projects, such as the use of multipurpose spaces and the consolidation of small-scale functions, can assist in restoring and improving the livability of historical and deteriorated neighborhoods even in crisis conditions. The findings suggest that multipurpose spaces, by offering diverse services and enhancing resilience, can lead to improved quality of life and increased satisfaction among residents.Conclusion: The results of this study indicate that the inequitable distribution of services and facilities can challenge urban crisis management and significantly diminish both city resilience and quality of urban life. Each neighborhood, in accordance with its population size, requires access to essential functions such as commercial, educational, green spaces, recreational, and healthcare facilities to address residents' basic needs at least in the initial hours of a crisis. Transitioning from traditional planning methods to modern approaches, including the use of advanced models and software, alongside urban futures studies, can lead to significant improvements in post-crisis conditions. https://gisj.sbu.ac.ir/article_104819.html Introduction and Purpose: Generating Land Surface Temperature (LST) data with temporal and spatial continuity is in great demand for hydrology, meteorology, ecology, environment, and, etc. studies. Approximately, 60 to 75 percent of the Earth is covered by clouds at any given moment. Therefore, clouds, by creating an obstacle, absorb part of the thermal energy emitted from the earth by affecting thermal infrared energy, creating gaps and outliers in LST time series data. Removing the effect of cloud cover is always a common problem in the field of using satellite images. The purpose of this research is to evaluate the performance of Multi-channel Singular Spectrum Analysis (M-SSA) in order to reconstruct gaps and remove outlier data due to the cloud coverage in the hourly LST time series of the Meteosat-9 satellite.Materials and Methods: The study area in the present research was whole Iran. Also, the hourly LST time series of the SEVIRI sensor from the Meteosat-9 geostationary satellite in 2022 was used. At first, using SSA software and the Monte Carlo test, the window size and the number of significant components of an hourly LST time series were determined. Then, using the identified significant components, LST time series were reconstructed using M-SSA algorithm. Reconstruction error in clear sky conditions with available time series data and reconstruction error in cloudy sky conditions by creating artificial missing data (artificial cloud) with intensities of 10, 20, 30, ..., 90% in time series were evaluated using root mean square error (RMSE) and coefficient of determination (R2) statistics.Results: On average, in Iran, 25.5% of the hourly LST time series in 2022 was lost due to cloud cover, and the highest percentage of lost data was observed at the edge of the Caspian Sea. The results of analyzing the annual hourly LST time series in a window size of 96 hours with the Monte Carlo test showed that components 1 to 5 are significant components of this time series. These components control 97.5% of the LST time series variance. The frequency of the first, second-third, and fourth-fifth components are respectively 0, 0.042 and 0.083 cycles per image. The first component indicates annual periodic changes, the second and third components indicate 24-hour or daily temperature changes, and the fourth and fifth components indicate 12-hour periodic temperature changes. Based on the results, the RMSE and the R2 between the original and the reconstructed data in clear sky conditions were 1.38 and 0.99 Kelvin, respectively. Also, in cloudy sky conditions, the RMSE error up to the level of 80% of randomly lost data (artificial cloud) was always less than 2.1 Kelvin.Discussion and Conclusion: The main key to reconstructing time series with periodic behavior is to identify significant periodic components and trends. In hourly LST time series, annual, 24-, 12- and 8-hour periods are the most important components of the time series. These components are formed due to the rotation of the earth around itself and the sun and the deviation of its axis. Therefore, these components are generally the same for the reconstruction of hourly LST time series in the major part of the globe. Based on the findings, M-SSA algorithm can be effective in reconstructing lost data with large distance in LST time series due to consideration of periodic components and trends as well as using temporal and spatial correlation. One of the significant cases in reconstructing the effect of cloud cover in the present study and many other studies is the reconstruction of LST with the clear sky condition. Therefore, reconstruction of LST under cloud cover can be a challenge and suggestion for further studies in the future. https://gisj.sbu.ac.ir/article_104850.html Introduction: Desertification is one of the major challenges of today's world, threatening environmental sustainability. This phenomenon arises from land degradation in arid and semi-arid regions and can have serious consequences for the environment, economy, and society. Due to its geographic location in the dry and semi-arid belt of the world, Iran is at risk of desertification. To combat this phenomenon, it is essential to identify and assess the influential factors, determine vulnerable areas, and use models to evaluate this issue. The use of remote sensing technologies and Geographic Information Systems (GIS) can be beneficial in assessing and monitoring desertification. These technologies enable comprehensive and accurate examination of land cover changes and assist in the management and protection of at-risk areas. This study aims to identify areas susceptible to desertification in the eastern belt of Iran (Sistan Suture Zone and Afghan Blocks) using multi-criteria decision analysis models based on the Ordered Preferential Approach (OPA).Materials and Methods: The geological zone of Sistan and the Afghan Blocks, covering an area of over 106,000 square kilometers, is located in the eastern belt of Iran and includes parts of Sistan and Baluchestan and South Khorasan provinces. According to the De Martonne climate classification, this area falls within the arid and hyper-arid climate zones. Such conditions, along with vegetation degradation and the drying up of water resources, have made this region susceptible to desertification. In this study, to obtain a map of areas prone to desertification, wind and water erosion potential maps were first generated using the RWEQ and RUSLE models, respectively, in the study area. The results of these models, along with other indicators such as vegetation cover, soil salinity, land use, temperature, soil classification, bulk density, and climate classification, were weighted using a multi-criteria decision analysis model based on the Ordered Preferential Approach (OPA). Finally, a map of areas susceptible to desertification in the eastern belt of Iran was produced.Results and Discussion: The results of this study showed that the average wind erosion potential in the eastern belt of Iran is 64 kg per square meter. Notably, 16% of this area, primarily located in the eastern and southeastern parts, including the cities of Zabol, Saravan, and Khash, has a wind erosion potential exceeding 512 kg per square meter. In contrast, the average water erosion was found to be 24.36 tons per hectare, with the highest rates of water erosion exceeding 40 tons per hectare covering 34.5% of the study area, primarily in the northern region, including the city of Nehbandan in South Khorasan province and central parts of the area. Finally, the results of the multi-criteria decision analysis model based on the Ordered Preferential Approach indicated that the most significant factors identified by experts in recognizing areas susceptible to desertification in this region are wind erosion, vegetation cover, and soil salinity. The eastern and southeastern parts of the area are severely affected by desertification.Conclusion: Erosion in the eastern belt of Iran has multiple negative consequences, including reduced soil fertility and threats to livelihoods, food security, and public health. The degradation of vegetation, loss of water resources, and conversion of these areas into barren lands, particularly in the eastern half of Iran, which has faced extensive drought in recent years, have had the most significant impact on desertification. To deal with this problem, there is a need for management such as resource management, sustainable agricultural development and biodiversity conservation. These initiatives should be designed and implemented considering the specific conditions of each region and with the participation of local communities and experts. The results of this study indicate that the use of models based on the Ordered Preferential Approach can be effective in identifying vulnerable areas for the formulation of effective management plans. Additionally, incorporating indicators such as grazing management, population, and groundwater levels in future studies will facilitate a better assessment of desertification status. https://gisj.sbu.ac.ir/article_104998.html Introduction: Proper flood management requires the exact location and time of flooding so that crisis management planners can reduce the risk of flooding with proper management by providing solutions. Studies in this field have been carried out by researchers with different methods such as the use of Sentinel 1 and Sentinel 2 satellite gauges and it has been proven that flood monitoring with the help of remote sensing is a suitable tool for the quick direction of the flooded area. It is used in the early management of natural disasters, especially floods. The purpose of this study is to prepare a map of the extent of water caused by the flood of June Zanjan 1402 with the help of Sentinel 1 images. This map can be used in the management and planning of land users in flood plains, raising the level of awareness and warning people about flood spots. In the region, the development of flood risk reduction plans, the preparation of comprehensive flood risk management plans, and the preparation of guidelines for dealing with and resilience to critical conditions are contracted.Materials and Methods: The research method was carried out in steps: in the first step it was collected with the help of Sentinel-1, then in the second step: SAR data were pre-processed. The third step: the images were post-processed in the ENVI environment, with the help of the tree algorithm, and in the last step: the images were converted into vector files.Results and Discussion: Examining the changes in flooding after seven days of flooding in the region shows that the highest water level in the northern regions of the province is in the vicinity of the main and sub-rivers of the Qezal-Ozen watershed, especially in Tarem city. It was land with 312/067192, after which more number of polygons were seen in the north of Zanjan city in the area of Qezl-Ozen aquifer basin, Lower Zanjanrud, Pare, Ghani-Biglo, higher aquifer with the area of 150/713193, which these aquifers has taken more It has occurred under the impact of tectonics in the region around Qezl-Ozen river. Most of the flood water was seen in Mahenshan, in the northern part of Mahenshan city, in Mahenshan and Uriad divisions with 375 polygons and the extent of flood water was 26/618086. In Ijroud city in Zarin Abad, in the direction of the Ijroud river, most of the flood water was in the direction of the Ijroud river with the extent of 21/06405 and with flooding of 24 polygon centers, in Abhar city, the water is from the flood in Soltanieh center in Zangan. The river (one of the branches of the Qezal Ozen River) with an area of 96 lands was seen as a face with 547 flood polygons around the river.In the flood of June 1402 in Zanjan province, the height of the area was a key factor in controlling the direction of the flood and the persistence of water on the ground (5-b). The amount of flood water receding at altitudes less than 500 meters was very low compared to higher altitudes, in such a way that water retention was not seen at altitudes above 1000 meters, in the high places of Zanjan such as parts of Tarem, Zanjan and Mahenshan after Atmospheric precipitation had started to flow faster from the low-lying and flat areas, so that after seven days of the flood, water retention was not seen in these heights. While at altitudes of less than 500 meters, which mainly included the low altitude areas of the Qezl-Ozen catchment and its main and tributary rivers, most of the runoff was collected in the topographic holes of Tarem and Zanjan, in these low-lying areas. The region caused widespread flooding and flooding even in the population centers of these regions.Conclusion: In the upcoming research, in order to measure the extent of water caused by the flood and to prepare a flood zoning map for the month of June in Zanjan province and to evaluate the factors affecting it such as height and vegetation, Sentinel-1 images were prepared for before and after the flood. It was processed and classified into three classes and analyzed, and it was found that the largest amount of flood that entered Zanjan province was from the north of the province, especially Tarem city. Also, the study of the height factor in the flooding of the region showed that the heights of less than 500 meters, which mainly included the sub-basins of Qezl-Ozen and the rivers around it, had a high potential for flooding. Flooding also showed that the grassland vegetation has increased the flood potential of these areas due to insufficient permeability of rainfall in these areas. https://gisj.sbu.ac.ir/article_104997.html Introduction: Determination of organic-carbon-content variation in the field is crucial due to the importance of soil organic carbon content, including its role in increasing soil resistance against wind and water erosion. This study examines the ability of reflectance visible-near infrared (Vis/NIR) spectrometry for measurement and prediction of soil organic carbon content and the effect of the type of spectral preprocessing on the accuracy of multivariable predictive models was studied.Material and Methods: In this research, spectroscopy of soil samples was performed at 7 moisture levels in the interactance measurement mode in the 350-2500 nm spectral range using a contact probe. Spectrophotometry of 5 different sections of each soil sample was carried out and the data were processed and analyzed. Spectral data obtained from the spectrophotometer included unwanted information, background and noise in addition to the information of the samples. In order to arrive at accurate and reliable analytical models, pre-processing of the spectral data was required prior to regression model simulation. Multivariate calibration models of partial least squares (PLS) were developed based on the reference measurements and the information of the preprocessed spectra using a combination of different methods for assessment and prediction of soil organic carbon content. These included: smoothing (moving average (MA), and Savitzky-Golay (SG)); normalizing (multiplicative scatter correction (MSC), standard normal Variate (SNV)); as well as increasing the spectral resolution (first and second derivatives (D1, D2)).Results and Discussion: Results showed that NIR spectroscopy is a suitable method for measurement of organic carbon content in soil samples. Prediction utilizing the data analyzed using the PLS model based on SG + MSC, produced the best detection results. Thus, SG+MSC preprocessing (Rc2 =0.81, RMSEC = 0.239, Rp2 = 0.79, RMSEP = 0.252) is suitable for predicting the amount of soil OC with high accuracy (SDR= 3.191). Results showed that reflectance rate diminishes with increasing moisture content reducing the ability of the PLS model to predict organic carbon content. This is true across all the preprocessing methods. In addition, the determined index values and validation criteria showed that prediction of organic carbon content with the PLS model using SG+D1+MSC, SG+MSC, SG+MSC, SG+D1+MSC, SG+SNV and SG+SNV combinations gives the best detection results for the following moisture levels, respectively: 6, 12, 18, 24, 30 and 36%.Conclusion: Vis/NIR spectroscopy can be used as an alternative to conventional laboratory methods for soil organic-carbon-content determination. Results showed that the use of Vis/NIR spectroscopy for determination of soil organic carbon content can be considered in the site-specific management of fields, which can ultimately lead to saving inputs and reducing the pressure on the environment.. https://gisj.sbu.ac.ir/article_105144.html Introduction: Considering that the value and usability of any map produced from satellite images depend on its accuracy, evaluating the accuracy of satellite image classification methods is of great importance. Therefore, this research aims to analyse the performance of Support Vector Machine (SVM), Random Forest (RF), and Maximum Likelihood Classification (MLC) algorithms in identifying land use and land cover (LULC) in the metropolitan area of Mashhad. Numerous algorithms have been developed for satellite image classification to date, and their performance varies under different conditions. For this reason, this study first identifies the most commonly used algorithms through a review of previous research, and then, by assessing the characteristics of various classifiers, selects the three algorithms: Support Vector Machine, Random Forest, and Maximum Likelihood. There are various studies regarding the performance of different classification algorithms, each yielding different results. Given that multiple studies have shown that LULC mapping accuracy is related to time and location, and that each of these studies has emphasized the accuracy of different algorithms, their results cannot be generalized to the geographical conditions of Iran. On the other hand, there has not been sufficient research in the geomorphological conditions of Iran to assess the accuracy of classification algorithms, and most studies validating these algorithms have been conducted in case studies outside of Iran. Therefore, considering the differences in algorithm results under various conditions, examining the accuracy and performance of these algorithms focusing on the extensive and diverse metropolitan area of Mashhad may yield novel and noteworthy findings.Materials and Methods: The present research is applied in terms of purpose and descriptive-analytical in terms of nature. Data collection in this study has been conducted through a documentary-library method. In this study, images from the OLI sensor on the Landsat 8 satellite were used. The classification of satellite images was performed in two stages: preprocessing and processing. After assessing the accuracy of the classification using the Kappa coefficient, confusion matrix, coefficient of variation, and User's accuracy and Producer's accuracy coefficients, the best algorithm for classifying land uses in the metropolitan area of Mashhad was determined in five classes: 1- Built-up areas, 2- Barren land, 3- Mountainous areas, 4- Green spaces, and 5- Water bodies. Results and Discussion: The results from the evaluation of standard deviation (SD) and coefficient of variation (CV) regarding the area share percentage in a LULC class by various algorithms indicate that barren lands were classified with higher accuracy, while water bodies and green spaces were classified with lower accuracy. The examination of U_Accuracy and P_Accuracy coefficients shows that the overall accuracy of the classification for all studied algorithms falls within the range of good to excellent. However, a more detailed examination of these algorithms reveals that the greatest challenge in class identification lies in built-up areas, mountainous regions, and green spaces, whereas the identification of barren lands faces fewer challenges. The Kappa coefficient and analyses based on the confusion matrix also demonstrate the variation in accuracy among each LULC classifier. The differences in the accuracy of the classifiers used are marginal, but these slight variations hold significant importance in the context of LULC planning. Given that these marginal differences are evident in sensitive land uses such as built-up areas and green spaces, selecting an algorithm with the highest accuracy and lowest error is of special importance. Conclusion: The results of the Kappa coefficient evaluation and confusion matrix analyses indicate that the SVM approach has greater overall accuracy and a higher Kappa coefficient compared to RF and MLC methods. Specifically, the algorithms achieved overall accuracies of 0.93, 0.88, and 0.80, respectively. Therefore, Support Vector Machine demonstrates the highest accuracy and least error among the studied classifiers. Considering that numerous studies have shown that LULC mapping accuracy is related to time and location, it is suggested that future research analyse the accuracy of classifiers under different morphoclimatic and geomorphic conditions. https://gisj.sbu.ac.ir/article_105853.html Introduction: The optimal use of agricultural land is a key concern for authorities due to agriculture's significant role in job creation, foreign exchange earnings, ensuring food security, and reducing reliance on imports. Gathering information about the spatial distribution and cultivated areas of various crops can enhance their efficient usage. One effective method for obtaining this information is through satellite imagery. Remote sensing technology, with its ability to provide high-resolution images and extensive spatial and temporal coverage, has become a dominant approach for crop type mapping. One of the remote sensing data that has recently received attention in the field of crop type mapping is the interferometric coherence images of synthetic aperture radar (InSAR). The sensitivity of these images to crop’s structure, making them valuable for monitoring and mapping crop types. In global literature, InSAR coherence images have been widely used in research related to agricultural products. However, in Iran, the use of coherence data for monitoring phenology and distinguishing different crops has not received much attention, despite its unique capabilities. Therefore, evaluating the efficiency of coherence data and its potential for adopting optimal agricultural management policies in Iran can be highly beneficial.Methodology: The main objective of this study is to evaluate the efficiency of machine learning-based InSAR coherence data for crop type mapping. To achieve this, a one-year time series of Synthetic Aperture Radar (SAR) data was compiled from Sentinel-1 phase information for the 2019 crop year, for the Ardabil plain, located to the west and northwest of Ardabil city. A network of SAR image pairs with short spatial and temporal baselines was created to produce coherence data. Field data were collected from 1,358 fields containing various crops. To avoid mixed pixels, a 10-meter buffer was established around the edges of each crop field. A total of 156,026 pixels from the coherence images were sampled and randomly divided into three groups: training (70%), validation (15%), and test (15%). To select the appropriate time interval for using coherence images, the phenological response of the crops to the InSAR coherence was analyzed. During the time interval, the phenological signals of the studied crops were compared with the signals of the built-up areas and bare soil to ensure that they were not mixed. Consequently, the multi-temporal InSAR coherence values in the selected time interval were used as input to the Support Vector Machine (SVM) classifier with different kernels to distinguish and identify the type of crops.Result: The study of the coherence time series values in the selected control areas revealed distinct differences in the coherence behavior of various crops when compared to one another, as well as in comparison to both built-up and bare soil areas. The InSAR coherence data match well with the main phenological stages of the crops. Among the different SVM kernels tested, the radial basis function (RBF) kernel achieved the highest overall accuracy of 59.69% during the validation phase, utilizing various combinations of the parameters c and gamma. In the testing phase, the crop type map produced using the SVM classifier with the RBF kernel reached an overall accuracy of 60.6%. This model performed best in identifying wheat and least effectively in identifying alfalfa. User accuracy was notably higher for wheat and potato plants, while it was lower for corn, broad bean, and alfalfa.Conclusion: Coherence images offer valuable insights for identifying and classifying crops in Iran. Leveraging machine learning techniques can enhance the utility of coherence data in monitoring and categorizing different crop types. Several factors influence the effectiveness of coherence images and the performance of classification algorithms, including the number of training samples available for each crop, the number of coherence features, the use of complementary data, sensor parallax (spatial baseline), topographical features (slope and aspect), the temporal resolution, and the classification algorithm. These characteristics should be carefully considered to optimize the analysis. https://gisj.sbu.ac.ir/article_105953.html Introduction: In recent years, land cover has been recognized as a key indicator for assessing climate change, ecosystems, and the management of natural resources. Growing challenges in acquiring up-to-date and accurate data have led to the adoption of modern remote sensing technologies. Among these, the Sentinel-1 Synthetic Aperture Radar (SAR) imagery has emerged as a reliable source for land surface characterization. These images are produced by a SAR system using active microwave technology, enabling effective operation in all weather conditions. Therefore, this technology proves to be an appropriate tool for generating reliable and detailed land cover maps. The aim of this research is to improve the classification of land cover by simultaneously utilizing images acquired from both the ascending and descending orbits of Sentinel-1. In addition, the study investigates the impact of applying radiometric terrain flattening corrections on the overall accuracy of the classification results.Materials and Methods: This study examined three different regions in Iran: Marand, Sari, and Chadegan, which were selected due to their varied land cover characteristics and the presence of mountainous areas. The data used consisted of Sentinel-1 satellite images with VV and VH polarizations from both ascending and descending passes. Preprocessing steps included applying orbit file, thermal noise removal, border noise removal, calibration, radiometric terrain flattening, speckle filtering, Range-Doppler terrain correction, and conversion to decibels. Additionally, the data were rescaled to a specific range using the min-max normalization method. The Random Forest (RF) algorithm was then employed to classify land cover into five classes: water, soil, vegetation, urban areas, and agriculture. Finally, the results were evaluated using overall accuracy, the kappa coefficient, and class-specific accuracy metrics.Results and Discussion: The results indicate that the simultaneous use of ascending and descending images without applying radiometric terrain flattening significantly improves classification accuracy across all study areas. For example, in Marand, the overall classification accuracy increased from 65.33% to 79.17%, representing an approximate improvement of 13%. In Sari, the combination of images raised the overall accuracy from 55.67% to 75.41%, while in Chadegan, it resulted in an approximate 12% increase from 56.88% to 68.06%. Regarding class-specific accuracy, in Marand, the vegetation class improved from 43.41% to 69.64%, and in Sari, the soil class accuracy increased from 19.57% to 46.40%. Numerical analysis suggests that combining images from different orbits provides complementary perspectives of the Earth's surface, helping to reduce distortions caused by viewing angles and topography. In addition, the results reveal that while radiometric terrain flattening can enhance the accuracy of certain classes when using a single image, its application in the combination of two images may cause excessive similarity between some classes, ultimately reducing overall performance.Conclusion: In conclusion, this research highlights the importance of concurrently using Sentinel-1 images from both ascending and descending orbits, particularly when radiometric terrain flattening is not applied, which plays a crucial role in enhancing the accuracy of land cover classification. The observed improvement in overall accuracy, ranging from 13% to 20% across different study areas, underscores the strong potential of this approach for land cover mapping. Moreover, the findings of this study demonstrate that the preprocessing methods employed for Sentinel-1 images have a significant impact on the accuracy and efficiency of classification models. In some cases, applying radiometric terrain flattening can lead to a decrease in both accuracy and efficiency. Therefore, optimally combining Sentinel-1 data from multiple orbital passes can lead to more accurate and reliable land cover maps. The approach presented in this study can thus serve as a valuable reference for future studies in the field of remote sensing, particularly those focused on improving land cover classification for environmental and agricultural applications. https://gisj.sbu.ac.ir/article_105313.html AbstractIntroduction: This research examines and evaluates various methods of fusion satellite images to produce high accuracy land use and land cover maps in the Ahvaz region. Considering the importance of accurate land use information in natural resource management, urban planning, and sustainable development, this study aims to analyze different integration methods and investigate their impact on the accuracy of land use classification. In this context, two major levels of data integration are explored: pixel-level integration and decision-level integration. Pixel-level integration involves combining information from multiple images simultaneously at the individual pixel level, which can significantly improve the accuracy and quality of the final images. On the other hand, decision-level integration focuses on combining the results obtained from different classification algorithms.Materials and Methods: In this research, images from two sensors, Landsat 8 and Sentinel 2, were used. Landsat 8, with a spatial resolution of 30 meters, and Sentinel 2, with a spatial resolution of 10 meters, were specifically chosen for applications related to land use and land cover.In the first step, images were integrated at the pixel level using various integration methods, including Discrete Wavelet Transform (DWT), Spatial Filtering based on Intensity Modulation (SFIM), Gram Schmidt (GS), Multiplicative (MP), Brovey Transform and Principal Component Analysis (PC). Each of these methods was specifically designed to preserve the spectral and spatial characteristics in the integrated images.In the second step, two classification methods, Maximum Likelihood Classification (MLC) and Support Vector Machine (SVM), were employed to create classified images. This choice was made because of the high ability of both methods to differentiate various land use and land cover classes. As a final step, the use of the Dempster-Shafer method as a decision-level integration approach was examined. This method allows for the combination of evidence and information from various sources, facilitating the production of more accurate and reliable results.Results and discussion: The results of this study indicated that the Support Vector Machine (SVM) method achieved higher accuracy in land use and land cover classification compared to the Maximum Likelihood Classification (MLC) method. The land use classification derived from the SFIM image using MLC, along with those obtained from GS, PC, and Brovey using SVM, were selected for decision-level integration due to their high Kappa coefficient and overall accuracy. The final land use map obtained through Dempster-Shafer integration exhibited an overall accuracy of 98.38% and a Kappa coefficient of 97.67%. These results reflect an improvement of 5 to 7 percent compared to the four land uses utilized. The increase in accuracy in class differentiation signifies success in more precise identification and classification of land use classes. Furthermore, the results revealed that the Dempster-Shafer method provided significant improvements, particularly in distinguishing similar classes such as soil and residential-road, leading to a notable increase in producer accuracy for these classes.Additionally, the examination of confusion matrices showed that the application of the Dempster-Shafer method reduced ambiguity in the classification of various land use classes. This emphasizes that the correct selection of integration and classification methods can directly enhance the accuracy and quality of land use maps.Conclusion: This research clearly demonstrates that the use of the Dempster-Shafer method as an effective tool in integrating classified data can significantly increase the accuracy of land use maps. Moreover, this study emphasizes that selecting appropriate integration methods at both the pixel and decision levels can positively impact the quality of land use maps. Ultimately, this research serves as a valuable reference for future studies in the field of remote sensing data integration and its applications in natural resource management and urban planning, underscoring the importance of having accurate land use maps. https://gisj.sbu.ac.ir/article_105522.html Three-dimensional changes in urban environments have become one of the most critical topics in urban environmental studies and structural change monitoring. As cities rapidly expand and the number of construction projects continues to increase, identifying and monitoring these changes have gained significant importance. Furthermore, the ability to simulate and predict urban changes can help urban planners and decision-makers make informed choices. In this regard, the use of three-dimensional data, such as LiDAR point clouds, is an effective method for accurately simulating and detecting three-dimensional changes at the urban level. The primary objective of this research is to develop an algorithm for identifying and analyzing elevation changes in urban areas using bi-temporal LiDAR data processing techniques. These elevation changes can result from various factors, such as the construction and demolition of buildings, changes in land use, or variations in vegetation cover. In this study, LiDAR point cloud data from the years 2014 and 2019, collected from the coastal region of Duck in North Carolina, were utilized. These datasets contain three-dimensional points with X, Y, and Z coordinates, along with intensity values recorded from the Earth's surface using a LiDAR sensor. To identify elevation changes, the distance between the two point clouds was computed. The relative distance between corresponding points was determined using Delaunay triangulation, which created an irregular triangular network from one set of points and measured the distance between this network and the corresponding points in the other dataset. Following this step, a local adaptive thresholding method was applied to detect elevation changes at various scales. This method has the advantage of identifying localized changes more effectively than global detection techniques, which may overlook smaller variations. In this research, the two point clouds were merged into a single dataset to analyze elevation changes in urban environments. This process resulted in a unified point cloud with higher density in unchanged areas. In contrast, in areas where elevation changes occurred, multiple elevation surfaces emerged, leading to an increase in elevation variance. This effect was particularly noticeable in cases where land use had changed or where buildings had been demolished and reconstructed. The variance differences were clearly visible, providing strong indicators of real changes in the urban landscape. In regions experiencing changes, the elevation variance of the combined point cloud increased significantly, highlighting structural modifications. Conversely, in areas without elevation changes, the elevation variance remained low. This method proved especially effective in detecting minor changes that are often overlooked by conventional global change detection methods. To evaluate the accuracy of the proposed approach, key performance metrics such as completeness, correctness, overall quality, and the F1 score were computed. The results demonstrated that the proposed method performed exceptionally well in detecting elevation changes in urban areas. Specifically, in regions where changes in building heights or land use had occurred—such as the conversion of land into buildings or vegetation into urban structures—the algorithm successfully identified changes with high precision. In particular, for two subsets of the study area where building demolition and construction activities took place, the completeness metric exceeded 98%, while accuracy in other metrics ranged between 86% and 98%. For the third subset, where vegetation was converted into residential land use, completeness was measured at 85%, with accuracy in other metrics ranging between 83% and 98%. The local adaptive thresholding method introduced in this study effectively identifies elevation changes in complex urban environments. This technique is particularly efficient in detecting small-scale, localized changes that global methods may overlook. The results of this research have significant implications for urban planning, infrastructure monitoring, and disaster management, as they can enhance decision-making processes in these domains. Future studies should focus on applying this method to various urban environments while considering its computational efficiency and scalability for processing large-scale datasets. The integration of advanced machine learning models with this approach could further improve change detection accuracy and automation, leading to more efficient monitoring of urban transformations. https://gisj.sbu.ac.ir/article_105524.html Introduction: Change detection, one of the applications of remote sensing images and photogrammetric data, with a history of over four decades in various military and civilian domains, plays an important role in urban management, crisis management, monitoring natural resources, ensuring security, and governmental governance. Monitoring and controlling changes within the boundaries and urban areas, especially in addressing unauthorized land-use changes, is one of the most critical needs of urban management. For this purpose, using classical methods, despite their simplicity and accessibility, lacks the necessary efficiency due to limitations in accuracy, speed, and comprehensiveness. On the other hand, implementing new deep learning-based methods such as neural networks also faces challenges due to the difficulties in preparing training data, being time-consuming and costly, and requiring powerful computational and hardware resources. This paper aims to present a relatively fast, cost-effective, and high-accuracy process for detecting and identifying changes in residential areas.Material and methods: The proposed process, aimed at overcoming the limitations of previous methods, is based on the use of photogrammetric products, including Digital Surface Models (DSM) and orthophotomosaics, along with the application of various filters. The input data, with horizontal and vertical accuracies better than 30 cm, have been prepared and enable the identification of buildings that have undergone changes over time. The proposed process involves generating a Digital Difference Model (DDM) by subtracting two-time DSMs, which visualizes height changes in both positive and negative directions. Initial targets are then extracted by applying height and area threshold limits, combined with multiple filtering stages on the input data. To reduce recognition errors caused by factors such as shadows, vegetation, vehicles, and other existing features, orthophotomosaic classification using intelligent algorithms is performed and applied to the Digital Difference Model. This step reduces the impact of interfering features and leads to the extraction of the final targets.Results and discussion: To evaluate the performance of the proposed process, two study areas in Yazd Province were selected: one with a simple urban texture and the other with a complex urban texture. The data include orthophotomosaics with a pixel size of 10 cm for both study areas. Additionally, the Digital Surface Models (DSMs) have pixel sizes of 40 cm and 10 cm, respectively. It is worth noting that the time interval between data acquisitions was two months for the first study area and three years for the second. The results of implementing the proposed process achieved an overall accuracy of over 90% in the first study area and over 83% in the second. Optimal values for height and area thresholds and filter settings were determined through a trial-and-error process, by defining various events and precisely analyzing the counts of correct targets, missed targets, and false targets to achieve the highest accuracy. Analysis and evaluation of the proposed process show that applying appropriate filters in four stages increased the overall algorithm accuracy by more than 30%.Conclusion: The proposed process is highly dependent on the study area and the threshold values corresponding to its urban texture. Despite this limitation, the presented method, due to its lower cost and higher speed compared to similar methods, has broad applicability in areas similar to those studied. Additionally, the results of this paper show that this process, due to its high accuracy and acceptable results, can serve as an effective tool in the field of urban management and monitoring authorized and unauthorized changes, contributing to improving decision-making processes in this domain and effectively addressing the need for urban boundary control. For other areas with textures different from those in this study, it is necessary to calculate optimal values for operational components and thresholds using a similar methodology. https://gisj.sbu.ac.ir/article_105525.html Introduction and Objectives: The advent of digital sensors, smartphones, crowdsourced applications, and vibrant social media platforms has dramatically transformed the landscape of geographic data accessibility. This transformation is even more pronounced with the emergence of user-generated content, a hallmark of Web 2.0 technologies. This participatory phenomenon is termed Volunteered Geographic Information (VGI), of which OpenStreetMap (OSM) serves as a prominent illustration. OSM offers an extensive repository of detailed and frequently updated geospatial data concerning physical infrastructures, including buildings, roads, and other vital landmarks. Though OSM provides this wealth of data free of charge and continues to expand its database, the quality of the information necessitates meticulous evaluation to determine its suitability for various practical applications. Research across the globe has underscored the efficacy of VGI; however, there remains a significant gap in studies investigating the quality of spatial information pertaining specifically to buildings within OSM, particularly in regions like Iran. This study aims to address this gap by focusing on three critical aspects: first, it will evaluate the quality of building data captured in OSM; second, it will analyze the enhancements and overall completeness of this data from the years 2018 to 2023; and third, it will explore the intricate relationship between land use patterns and population density, utilizing the building data derived from OSM. Through this comprehensive examination, the study hopes to shed light on the integrity of VGI in representing urban landscapes.Materials and Methods: The study area, encompassing districts 9 and 11 of Mashhad, was divided into a grid of 1 x 1 km cells, serving as the foundational framework for our analysis. Within each cell, we assessed three key metrics from 2018 to 2023: building density, completeness, and the quantity of buildings documented in OpenStreetMap (OSM) data. Notably, the ratio of officially registered charges to the overall count of charges within the voluntary dataset indicates the extent to which official data is represented in the voluntary dataset. This metric reflects the completeness of the voluntary data relative to official sources. Subsequently, we analyzed the correlation between building density and data completeness for each grid cell. Additionally, demographic parameters, including population and land use, were incorporated into the evaluation process.Results and Discussion: The construction data sourced from OpenStreetMap (OSM) across the 9th and 11th districts of Mashhad has witnessed an impressive twentyfold increase from 2018 to 2023. This extraordinary expansion is particularly evident in the eastern and northeastern sectors of the city, where development has surged. Among the various land use categories identified, residential areas, followed by residential-commercial zones, commercial spaces, and educational institutions, display the highest frequency of construction activities in that specific order. Moreover, there exists a notable and robust correlation between the OSM building data and the population residing within each building block. However, this connection has exhibited significant fluctuations throughout the analyzed period, indicating varying patterns of growth and development. Furthermore, an intriguing relationship emerges between the density index and the completeness of the data; in regions where the density of OSM building data is greater, users tend to exhibit a heightened willingness to create and delineate new buildings, reflecting an active engagement in urban development.Conclusion: An in-depth examination of completeness index values reveals a noteworthy discrepancy in the OpenStreetMap (OSM) dataset, which significantly underrepresents the actual number of buildings when compared to official records. This research compellingly illustrates that, although OSM data can serve as a valuable resource for geographical analyses in urban environments—especially within bustling metropolises such as Mashhad—there exists a pressing necessity for enhancements and validation of the data to attain a higher level of accuracy. Moreover, a meticulous evaluation of key performance indicators can provide profound insights that not only enhance the reliability of the OSM dataset but also bolster its applications in urban planning and other related fields, thereby paving the way for more informed decision-making processes. https://gisj.sbu.ac.ir/article_105641.html ABSTRACT:Background and purpose:Indirect measurement of precipitation through remote sensing is a practical way to achieve a comprehensive estimate of precipitation and to better understand the phenomenon of precipitation and its effective parameters in a wide spatial area with high spatial and temporal resolution. On the other hand, in satellite precipitation products, due to the use of different algorithms and correction methods by using ground rain gauge observations, there is a need to check the accuracy of these satellite precipitation products in different parts of the globe. Two satellite precipitation products with high and accurate temporal and spatial resolution in the new era are: 1-GPM-IMERGE precipitation product with a spatial resolution of 0.1 degrees and a temporal resolution of 0.5 hours, which is presented in three versions. 2- GPM-GSMAP rainfall product with a spatial resolution of 0.1 degrees and a time resolution of 1 hour, which this satellite rainfall product often provides in three versions. Most of the researches comparing the GSMAP and IMERGE products have compared these two products on a daily and larger time scale, and there are rare studies on an hourly scale. The purpose of this study is two research satellite precipitation products GPM-IMERG_F and GPM-GSMaP_G on a 6-hour scale (sub-daily) in East Azarbaijan province. Considering the lack of a dense rain gauge network in the region, along with the environmental disaster of drought in Lake Urmia, and the importance of rainfall information as a primary data in most water studies, it is necessary to move towards the use of satellite data to estimate rainfall in different areas; Therefore, it is necessary to evaluate the accuracy of these satellite precipitation products in the study area.Materials and methods:In this research, to evaluate the detection capability of satellite precipitation products, seven binary matching criteria including: probability of detection (POD), critical success index (CSI), false alarm ratio (FAR), Hick skill score index (HSS), bias frequency index (FBI), The correct ratio (PC) and the statistical index of true skill (TSS) and for the quantitative analysis of the accuracy of satellite precipitation products from six statistical indices including regression coefficient (R), root mean square error (RMSE), three bias indices (MBias, RBias, Bias) and the mean absolute error (MAE) index is used. Also, from the analysis of the Taylor diagram and the comparison of the spatial patterns of precipitation and the probability density curve of cumulative 6-hour precipitation and the performance of satellite precipitation products in terms of topography and altitude have been compared.Results:Despite the more accurate spatial and temporal resolution of both precipitation products, they still present a significant bias in some stations. Based on the Taylor diagram analysis, in all stations, the point corresponding to the IMERG_F satellite was closer to the observed point, and as a result, the IMERG_F product is better than the GSMaP_G product. Although both products had relatively similar spatial patterns in terms of statistical and binary indices, the GPM-IMERG_F product had much better accuracy and detection capability than the GPM-GSMaP_G product, so that the GPM-IMERG_F product has a cumulative probability density curve very close to the ground synoptic stations in terms of topography and altitude.Conclusion:GSMaP_G product has the best performance in the region. Compared to station observations, the IMERG_F product is underestimated, while the GSMaP_G product is overestimated. Compared to GSMaP_G, the IMERG_F product can better reproduce the 6-hour rainfall intensity PDF. In the region, the highest frequency of 6-hour rainfall occurs in the range of 0-0.1 mm and 5-10 mm in 6 hours, and the lowest frequency of rainfall occurs in the rainfall intensity of more than 20 mm in 6 hours. The IMERG_F product agrees well with the station observations in terms of frequency, when the rainfall intensity is greater than 1 mm in 6 hours. This study will be valuable to algorithm developers of these products as well as users of these products and can help in applications such as natural disaster risk reduction and hydrological modeling, especially in areas with a sparse rain gauge network. https://gisj.sbu.ac.ir/article_105642.html Introduction: Estimation of spatiotemporal patterns of precipitation is difficult in Mazandaran province due to several factors, including the lack of ground observations, diverse climate zones, and extreme mountain slopes. Satellite precipitation products can provide a suitable solution for measuring the amount of precipitation, especially in areas with scattered ground stations, and provide a new approach to observe precipitation globally with remote sensing. However, despite the wide use of these products in various fields of study, the quantitative evaluation of these products is a fundamental challenge due to their inherent error and uncertainty, which should be considered in different temporal and spatial scales before their direct use. Materials and methods: In the first step, CHIRPS, CMORPH, SM2RAIN, PERSIANN-CDR and IMERG gridded precipitation products were extracted from the database of each product in NetCDF format at the global level. Then, precipitation data for each product was selected for grids located in Mazandaran province by coding in the R programming environment and Geographic Information System (GIS). In the next step, the evaluation and comparison of these products against 15 synoptic stations in the Mazandaran province at the station-grid and regional spatial scales and monthly and annual time scales using the statistical evaluation criteria of Spearman's correlation coefficient (CC), Root Mean Square Error (RMSE), Mean Absolute Error (MAD), Kling-Gupta efficiency (KGE) and Nash-Sutcliffe efficiency (NSE), as well as drawing statistical diagrams (Taylor, etc.) were performed. In order to evaluate the grid to the station, the data of the closest grid to each synoptic station was extracted for each precipitation product and compared with the precipitation data of station in different time scales. Results and discussion: The results of the regional evaluation of satellite precipitation products on a monthly and annual scale have shown that the IMERG and CMORPH products are more compatible, while the CHIRPS product performed well only in the dry months of the year. However, the accuracy of the products was higher on a monthly scale than on an annual scale. The Taylor diagram results indicated relatively high accuracy of IMERG, CHIRPS and CMORPH products (correlation 0.8-0.7) at stations located in coastal areas and relatively low accuracy at high altitudes (correlation 0.35). While for the PERSIAN product, the data accuracy was low for all regions, with a negative correlation in coastal areas. However, the results of the evaluation of precipitation products at the station level showed the better performance of the IMERG product and then CMORPH (CC=0.7-0.8 and RMSE=2-4 mm) in estimating monthly precipitation mainly in the eastern half of the province. While the lowest accuracy and the weakest performance was for the PERSIANN-CDR product. The highest CC value of precipitation products was equal to 0.8, which was mainly in the eastern and coastal areas of the province, but the lowest value was related to the PERSIANN-CDR product (CC=0.05). The RMSE values are mainly between 2 and 15 mm in the mountainous and eastern half of the province, respectively, and the lowest values are for the IMERG and CMORPH products. The values of KGE and NSE were also closer to the optimal value mainly in the coastal and eastern areas (NSE=0.5 and KGE=0-1), which was better for the CMORPH product. However, the BIAS values for all products varied between (-4)-2 mm, which was underestimated in coastal and low-altitude areas, but overestimated in high-altitude areas. Investigating the effect of the distance between the synoptic station and grid precipitation on the accuracy of the precipitation product has also shown that for the CMORPH, IMERG (in high areas) and SM2RAIN products, a low (higher) distance between the station and the grid has reduced (increased) the uncertainty. However, for most of the precipitation products, the significant increase in elevation has increased the uncertainty in satellite precipitation estimation.Conclusion: The most accurate precipitation product in Mazandaran province includes the IMERG product. One of the main problems in the accuracy of precipitation products in this region is the complex topography (large height difference) and the proximity to the Caspian Sea. However, the use of modern methods such as remote sensing systems as a solution for estimating precipitation represents scientific advances in this field, and this can be used as a guide for decision-makers in climate and hydrological studies. https://gisj.sbu.ac.ir/article_105673.html In recent years, the architecture and construction engineering industry has been moving from 2D to 3D (Building Information Modeling) to enable better visualization and sharing of information. With the development of this industry in high-rise buildings such as department stores, hotels, hospitals, and cultural centers, the need for an indoor navigation system is increasingly felt. The main goal of this project is to present and produce an operational route in the interior spaces of the building by integrating the building information model and the geographic information system with two improved triangulations and meshing methods and their graphical display. Therefore, this project seeks to study and route a real example and during its implementation, we will examine the effect of various parameters on the performance of the developed model. One of these parameters is the change in the dimensions and structure of the meshes with the aim of improving performance and increasing accuracy in modeling. The designed routes also include options for choosing between stairs and elevators. In this way, users can easily identify the best route based on the conditions and constraints to reach their destination. Choosing the right route according to the different needs of users, including those with mobility problems, can provide an optimal and comfortable experience. Also, in this project, in addition to reducing the length of the route, time optimization is also discussed, because in the routing process, two parameters of time and distance must be considered and decisions made based on the priority of each of them. The building information model includes precise details of different parts of the building in three dimensions. This model allows architects and project engineers to achieve a more complete and comprehensive understanding of the structure and technical characteristics of the building. However, it does not have the ability to analyze the route network. Geographic information systems with spatial analyses enable route optimization and help increase efficiency, accuracy, safety, and accessibility in complex environments. Combining a building information model with a geographic information system can help with internal routing and provide conditions for improving the management of the routing process. For this purpose, the present project examines a six-story office building in Rasht. First, the two-dimensional plans are converted to three-dimensional using the Revit Architecture software, which is based on the building information model, and after data integration, the final generated routes will be displayed graphically in ArcGIS Pro software. Finally, the software output will be studied and examined for different scenarios. The results show that the improved meshing method has higher accuracy and provides better coverage of the building floor space, and performs better than the triangulation method on routes without complications and breaks. On the other hand, on routes with many breaks, arcs, and longer routes, the triangulation method performs better than the improved meshing method. In general, it is not possible to choose one method as the best option, because each method performs differently depending on the type of environment and the topic under discussion. It seems that the combined use of methods can be an effective solution, because in some cases the advantages of one method can compensate for the weaknesses of another. In conclusion, it can be stated that the indoor navigation system can help reduce access problems and increase efficiency in the use of public spaces. Optimal navigation in critical situations helps reduce risk and increase the safety and peace of mind of users in complex and large environments. This allows users to quickly and with minimal risk access to exit points or safe places. In addition, this process also helps to make buildings smarter and, as a result, cities smarter. https://gisj.sbu.ac.ir/article_105674.html Introduction: Albedo is one of the key parameters in environmental studies that shows the ratio between the solar radiation reflected from the Land surface and the solar radiation incident on it. In Iran, many studies have been conducted on the Land surface albedo at the local and national levels. In some studies, the zoning of the Land surface albedo and the factors affecting it have been studied. In some studies, the trend of the Land surface albedo has also been studied. However, no research has been conducted on the albedo time series of Iran at the macro and national levels. Therefore, studying examining the albedo time series in Iran can be a step towards revealing its environmental changes over the last two decades. Data and Methods: The MODIS sensor is mounted on two satellites, Terra and Aqua, which were launched by NASA on December 18, 1999, and May 4, 2002, respectively. These two satellites image the entire land surface twice a day. MODIS sensor produces the land surface albedo with appropriate spatial and temporal resolution and makes it available to researchers. In this study, in order to analyze the time series of Iran's albedo, daily albedo data of MODIS sensor in Iran were downloaded from NASA website in the period from 1/1/1379 to 29/12/1401 for 8402 days. After mosaicking the tiles using the Frequency function in MATLAB software, daily, monthly, seasonal, and annual time series of Iran's albedo were calculated. Results and Discussion: The results of the time series on an annual scale showed that the highest albedo of Iran during the last two decades occurred in 2007 with a value of 14 percent. The lowest albedo of Iran was recorded in 2009 with a value of about 11 percent. Seasonal time series studies also showed that the highest and lowest albedo of Iran during the last two decades occurred in the winter of 2007 and the fall of 2018, respectively. The monthly time series results also indicate that the highest albedo of Iran during the last two decades occurred in January and especially in February of 2007 with a value of 28%. The lowest albedo of Iran was also recorded not in July or August but in December of 2005. This shows that the albedo of Iran has a bimodal behavior; that is, one peak is observed in the winter due to increased snow cover and one peak is observed in the summer due to increased temperature and dryness of the land surface.Conclusion: According to scientific statements, among the phenomena of the land surface, the highest of the land surface albedo is specific to snow and the lowest of the land surface albedo is specific to water and dense vegetation. A large area of Iran is poor in terms of snow cover. On the other hand, snowfall occurs only in a short period of the year. Therefore, the average albedo of Iran over the last two decades has been recorded at about 12 percent, which is insignificant compared to the global average (30 percent). The results of the time series on a daily scale showed that the lowest albedo of Iran over the last two decades occurred on December 2, 2018, which seems to be the day when precipitation systems were active in the country and a large area of the country was covered with precipitation. This seems natural considering the widespread flood of 2018 that occurred over a large area of the country and requires a separate study. On this day, the average albedo of Iran was calculated to be only 9 percent. The time series on a daily scale also confirmed that the maximum albedo of Iran was in the winter of 2007. The results showed that on January 19, 2007, Iran's albedo reached 38 percent, which suggests that heavy snow occurred in Iran on that day, which requires a separate study. https://gisj.sbu.ac.ir/article_105737.html Introduction: Building footprint information, as one of the most important elements of spatial data, plays a key role in many urban applications, including urban planning, infrastructure management, environmental studies, and sustainable development (Haghighi Gashti et al., 2024; Zhao & Wang, 2014). Accurate and up-to-date access to this information can provide a suitable foundation for managerial decision-making. Extracting this information from high-resolution aerial and satellite images is one of the main challenges in the field of remote sensing and spatial data analysis (Bittner et al., 2018). In recent years, machine learning and deep learning algorithms have gained attention as advanced tools to address this problem. The main objective of this research is to compare the performance of two common approaches in the field of artificial intelligence—deep learning and machine learning models—for extracting building footprint information from high spatial resolution aerial images. In this regard, the U-Net model and the XGBoost model were examined to comprehensively evaluate these two models in terms of accuracy, the ability to detect precise building boundaries, and other quantitative metrics, with the aim of selecting the most appropriate method for practical applications in the field of geographic information systems.Materials and Methods: For this study, a dataset consisting of aerial images from four different cities—Chicago, Paris, Zurich, and Berlin—was used. These images featured appropriate spatial and structural diversity, and their building footprint information was obtained from open-source data. The initial images were divided into patches of 512×512 pixels, and corresponding building masks were also generated. The data were then split into three parts: training (70%), validation (20%), and testing (10%). The U-Net model was trained using the Binary Cross Entropy loss function and optimized with the Adam algorithm. On the other hand, the XGBoost model, which is based on the combination of gradient-boosted decision trees, was trained using numerical feature extraction from images and tuning of various parameters, including tree depth, learning rate, and the number of trees. The XGBoost model parameters were selected through grid search.Results and Discussion: To evaluate the performance of both models, five main metrics were used: precision, Intersection over Union (IoU), accuracy, recall, and F1-score. The results showed that the U-Net model outperformed the XGBoost model in all evaluation metrics. Specifically, the IoU and Accuracy values for the U-Net model were reported as 67.74% and 87.95%, respectively, while for the XGBoost model, they were 55.07% and 75.67%. Additionally, the U-Net model was able to more completely detect the boundaries of buildings while preserving the spatial and structural information of the buildings. Due to its specific architecture—which includes direct connections between the encoder and decoder parts—the U-Net model can extract image features directly without the need for manual feature engineering. However, high computational resource consumption and the requirement for large training datasets are among the challenges of deep learning models. On the other hand, although the XGBoost model is relatively simple and faster, it showed weaker performance in detecting precise building boundaries, especially in urban areas with high density and irregular boundaries, due to its dependency on extracted numerical features and its inability to directly process images. In some cases, this model failed to accurately distinguish between buildings and other similar objects.Conclusion: The results of this study indicate that for applications such as precise extraction of building footprint information from aerial images—especially in areas with complex and dense urban structures—deep learning models like U-Net perform significantly better than machine learning models like XGBoost. However, in situations where training data are limited and computational resources are not available, using lighter models like XGBoost can also be beneficial. Finally, it is recommended that future research employ hybrid approaches to leverage the advantages of both models and improve the accuracy of spatial information extraction. https://gisj.sbu.ac.ir/article_105738.html ABSTRACTIntroduction: Corn, as one of the key agricultural products and a fundamental pillar of food security worldwide, is cultivated in all parts of the world due to its high resistance and adaptability to various climatic conditions, and has long been of interest to farmers due to its high production potential and diverse applications. The leaf area index (LAI) is a key parameter for assessing plant growth. Therefore, accurate measurement and continuous monitoring of LAI are essential for optimal management of corn fields and accurate crop yield prediction. The leaf area index is a key tool for assessing and monitoring vegetation cover changes. The main objective of the present article is to estimation the leaf area index of corn using satellite images in the Google Earth Engine platform and compare it with the output of the WOFOST model, which is innovative in two aspect among research in Iran: one is the use of the WOFOST model, and the other is the use of the capabilities of the Google Earth Engine platform in estimating LAI values and comparing the values with each other.Material and Methods: This study used Landsat 9 images from the 2023–2024 statistical period within the Google Earth Engine platform. The corn growing period in the Kalibar region of East Azerbaijan province, which spanned from April 14 to September 14, was determined using SMADA software. Additionally, we employed the WOFOST model to examine and compare the leaf area index (LAI) values of corn crops, a key crop for food security. For this purpose, NDVI, SAVI, and LAI indices were calculated. Additionally, r^2, RMSE, and MSE were used to verify the results.Results and Discussion: First, NDVI, SAVI, and LAI indices were calculated, with the lowest and highest NDVI on 2024/08/25 and 2023/04/24 being -0.228 and 0.691, and the lowest and highest SAVI on 2024/08/25 and 2023/07/22 being -0.342 and 0.937, respectively. The lowest LAI index recorded was zero, while the highest was 5.968, observed on July 22, 2023. The results showed that the RMSE and MSE values of the LAI index based on the WOFOST model were below 0.5 and were equal to 0.376 and 0.334, respectively. Also, the coefficient of determination (r^2) between the WOFOST model and satellite images is 0.857, and the highest LAI starts from day 185 of crop growth and continues until day 225. Additionally, the highest coefficient of determination (r^2) between LAI and NDVI is related to 2024/09/10 with 0.961, and the lowest is to 2024/06/06 with 0.795. The overall correlation value between the LAI index and NDVI is 0.937.Conclusion: The findings of this study demonstrate that integrating remote sensing data with crop growth simulation models such as WOFOST can be a powerful tool for monitoring and assessing vegetation dynamics, especially the Leaf Area Index (LAI). Spatiotemporal analyses of the SAVI and NDVI indices revealed that the southern and southwestern regions of the study area exhibited the highest values of these indices due to dense vegetation cover. Conversely, barren lands caused the lowest values in the north and east. A strong positive correlation between SAVI and NDVI (with a coefficient of determination of 0.857) confirms that these indices can be used complementarily to evaluate vegetation health and density. Furthermore, the high agreement between LAI values derived from satellite imagery and WOFOST model predictions (with low RMSE and MSE values of 0.376 and 0.334, respectively) underscores the model’s accuracy in simulating plant growth parameters. These findings suggest that calibrating dynamic crop growth models with satellite data can be a practical solution for rapid monitoring and yield prediction in large-scale agricultural applications. Keywords: Leaf Area Index (LAI), NDVI, SAVI, Google Earth Engine, Landsat, WOFOST. https://gisj.sbu.ac.ir/article_105739.html Background and Objectives: Air pollution, particularly particulate matter (PM2.5 and PM10), poses significant challenges in large urban areas, leading to severe impacts on public health, ecosystems, and overall quality of life. These issues are especially pronounced in densely populated cities such as Tehran, where air quality management is of utmost importance. Accurate monitoring and forecasting of air quality are essential for developing effective public health and policy strategies. However, the spatial limitations of ground-based air quality monitoring stations prevent comprehensive observation of air quality variations across the entire city. To address these limitations, this study utilized satellite imagery from Landsat-8 and Sentinel-2 to predict particulate matter concentrations, specifically PM2.5 and PM10. By combining spectral reflectance data with advanced machine learning methods, the research aims to identify efficient predictive models and determine the most influential spectral bands for estimating particulate matter concentrations.Materials and Methods: The study began by developing linear regression models using single-band reflectance and multi-band combinations to establish relationships between spectral data and particulate matter concentrations. To capture more complex patterns, nonlinear regression models were also examined. For optimal feature selection, a hybrid Genetic Algorithm-Support Vector Regression (GA-SVR) method was implemented. The Genetic Algorithm (GA) identified the optimal spectral band combinations, while Support Vector Regression (SVR) constructed robust predictive models based on these optimized features. Key evaluation metrics, including the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE), were used to assess and compare model performance. To ensure reliability and generalizability, data were divided into training (70%) and testing (30%) subsets, and cross-validation was applied to validate the models’ robustness.Results and Discussion: The findings revealed that the visible spectrum bands of Landsat-8 and Sentinel-2 showed strong correlations with PM2.5 and PM10 concentrations. Linear regression models developed using bands 1 and 2 of Landsat-8 and bands 2, 3, and 4 of Sentinel-2 achieved significant correlations in the training datasets. For Landsat-8, the R² values for PM2.5 were 70.56% and 67.24% for training and testing datasets, respectively, while Sentinel-2 reached an R² of 68.89% for the testing dataset. The RMSE values for Landsat-8 were 7.01 and 7.48 for the training and testing datasets, respectively, while Sentinel-2 demonstrated superior performance with RMSE values of 6.93 and 7.32. These results highlight the effectiveness of Sentinel-2 imagery in predicting particulate matter concentrations. In the nonlinear regression analysis, power models showed the highest R² values among the tested models. The normalized RMSE (NRMSE) values ranged between 0.066 and 0.115, demonstrating greater accuracy than linear models. Although nonlinear models proved more capable of capturing complex relationships, their high computational costs and only marginal accuracy improvements suggest that combining linear models with feature optimization is a more practical approach. The GA-SVR model yielded the best prediction accuracy, showing that shorter wavelengths play a crucial role in estimating particulate matter concentrations. With optimized feature selection, this model achieved an R² close to 70%, underscoring the potential of GA-SVR as a powerful tool for enhancing prediction accuracy in air quality studies.Conclusion: This study underscores the critical importance of visible spectrum bands in predicting air quality. Sentinel-2 imagery, when combined with the optimal spectral bands identified through the GA-SVR method, demonstrated superior accuracy in estimating PM2.5 concentrations. Linear regression models yielded reliable results; however, the integration of feature optimization and advanced machine learning methods significantly enhanced prediction performance. The GA-SVR model achieved remarkable accuracy, with R² values as high as 70.56%, underscoring the effectiveness of optimized models for precise and timely air quality monitoring across various spatial scales. These findings highlight the transformative potential of leveraging multispectral satellite imagery alongside machine learning techniques to address the complexities of urban air pollution, offering a robust framework for more informed environmental management and decision-making. https://gisj.sbu.ac.ir/article_105854.html The extraction of 3D geospatial information from the Earth’s surface using remote sensing and photogrammetric data has become a pivotal and widely utilized subject within the field of geosciences, attracting increasing attention from researchers in recent years. One of the most significant outputs of such data is the Digital Surface Model (DSM), which, in addition to representing the Digital Elevation Model (DEM), includes all natural and man-made features such as vegetation, trees, buildings, and other structures. DSM extraction plays a crucial role in a wide array of applications, including urban planning, building detection, disaster management, 3D modeling, and change monitoring. In recent years, remarkable advances in deep learning have significantly influenced the process of 3D information extraction from remote sensing data. Traditional 3D reconstruction methods often face challenges such as managing large datasets, complexity in extracting features, and difficulity in accessing acurate details. In this context, the use of deep neural networks for extracting complex features from multi-view images has introduced a transformative approach in this domain. A novel deep learning-based algorithm, Sat-MVSF, has recently been developed for DSM extraction from multi-view satellite images. This algorithm is designed to extract DSM from multi-view satellite images and performs all steps, from image preprocessing to final DSM generation, based on deep learning. Given the limited availability of training data and the authors' claims regarding the generalizability of the trained model weights, the objective of this study is to evaluate the performance of the Sat-MVSF algorithm in generating DSMs from high-resolution satellite images. The main innovations of this research include: 1) Preparation of three sets of WorldView-3 satellite data and two sets of ZY3-2 satellite data, involving block bundle adjustment for RPC refinement and reference DSM generation using LiDAR point clouds. 2) DSM extraction using the Sat-MVSF algorithm for multi-view images from both WorldView-3 and ZY3-2 sensors, followed by performance comparison against existing algorithms such as S2P and SS-DSM, as well as commercial software including CATALYST and ERDAS IMAGINE.To ensure a comprehensive evaluation, the performance of all algorithms is analyzed across three types of areas: (1) non-built areas, (2) building areas with moderate elevation changes, and (3) building areas with significant elevation changes. The dataset used in this study consists of five sets of satellite images—three from WorldView-3 and two from ZY3-2—with each set containing three overlapping images. The results demonstrate that Sat-MVSF outperforms many existing algorithms and commercial software in DSM extraction. For WorldView-3 imagery, Sat-MVSF achieves an average vertical accuracy of 1.1 meters and completeness of 87%, surpassing SS-DSM and commercial tools. On the other hand, S2P provides slightly better height accuracy (1.0 meters), suggesting Sat-MVSF is less precise in terms of elevation RMSE but still competitive. However, the performance of the S2P algorithm on the WV3-3 dataset is highly dependent on the study area, given that it has low elevation completeness. In the ZY3-2 datasets, Sat-MVSF achieves elevation accuracies of 2.43 and 3.27 meters, indicating acceptable performance. More specifically, in the first two WorldView-3 datasets, S2P attains the best performance with completeness of 90.76% and 90.16%, and elevation accuracies of 0.94 and 1.1 meters, respectively. In the third dataset, Sat-MVSF leads with a completeness of 83% and a elevation accuracy of 1.04 meters. The obtained results show that S2P performs best in building zones with significant elevation changes with accuracies of 1.03, 1.14, and 0.88 meters for the first, second, and third datasets, respectively and CATALYST application achieves the highest accuracy in non-built-up areas with values of 0.71, 1.12, and 0.68 meters across the same datasets. Overall, commercial software such as CATALYST and ERDAS IMAGINE exhibit higher height errors in built-up areas which have significant elevation differences. The reason for this is that these softwares use interpolation methods to fill gaps, which reduces accuracy in building areas with height differences. Given that if the height threshold limit is considered to be a large number in calculating the height accuracy and height completeness evaluation criteria, the error increases, meaning that pixels with a high height error are considered as correct pixels, and both the height accuracy and height completeness criteria will optimistically have a high value. At a small height threshold limit, both criteria will have a low value. https://gisj.sbu.ac.ir/article_106087.html One of the most important steps towards sustainable development is to protect the integrity of the land. Every year, a portion of the land changes, and removing such land from the production cycle causes irreparable damage. Since land use changes in the Khiav-Chai watershed are of great importance due to the specific conditions of this area, studying the spatial and temporal changes in land use provides valuable information to planners and managers for precise planning. Unplanned and unprincipled land use changes are considered significant and fundamental challenges for any country, and in turn, have highly destructive impacts on natural resources. Therefore, it is crucial to study and predict changes in land use. To model the land use changes in the study area, satellite images were used from Landsat 5 with the TM sensor and Landsat 8 with the OLI-TIRS sensor. By applying atmospheric corrections and using the supervised classification method with the maximum likelihood algorithm, the existing land uses in the region were classified into 6 categories. To generate the predicted land use change map for the year 2023, the land use maps of 1989 and 2007 were used as base and forward maps, respectively, and were input into the Markov chain model to predict the land use changes in 2023. Conditional probability plots, area transition matrix, and land use transition probability matrix were generated after modelling. Finally, the predicted map for the year 2023 was extracted using the STCHOICE tool. A fundamental limitation of the Markov chain in producing land use prediction maps is its inability to incorporate spatial information into the modelling process. To address this, cellular automata (CA_Markov) were integrated into the model to add the spatial element. The predicted map for 2023, including the spatial component, was generated by combining the cellular automata model with the Markov model and introducing the 1989 base land use map, the transition area matrix, and the conditional probability images. Then, land use maps for the next three decades (2033, 2043, and 2053) were predicted using the 1989 and 2023 land use maps. The accuracy of the maps was evaluated using the kappa coefficient and overall accuracy, while the validity of the maps was evaluated using the agreement and disagreement parameters. The satellite images of the years 1989, 2007, and 2023 for the study area were classified using the maximum likelihood method, and the land use map was extracted. It was found that the largest areas were occupied by rangeland, bare soil, and dry farming. The accuracy of satellite image classification was evaluated using an error matrix, and the kappa coefficient and overall accuracy were calculated as 72% and 82.87% for 1989, 83% and 88.40% for 2007, and 88% and 92.32% for 2023, respectively. Based on these results, it can be concluded that the classification accuracy of the images was acceptable. The analysis of land use changes in the study area showed that 119.7 ha of urban land, 354.42 ha of irrigated agriculture, 1039.05 ha of dryland agriculture, 2024.73 ha of bare soil, 3829.95 ha of rangeland, and 458.01 ha of snow cover remained unaffected between 1989 and 2007. Similarly, 123.12 hectares of urban land, 383.04 hectares of irrigated agriculture, 1282.32 hectares of dry agriculture, 2294.64 hectares of bare soil, 3704.04 hectares of rangeland, and 806.22 hectares of snow cover remained unchanged between 2007 and 2023. The area of land use in the predicted map for 2023 showed that urban land occupied 4.3%, irrigated agriculture 5.7%, dry farming 15.7%, bare soil 23.2%, rangeland 42.9%, and snow cover 8.2% of the study area. The accuracy evaluation results of the model showed an agreement of 0.84 and a disagreement of 0.16 between the predicted and actual maps, with a kappa coefficient of 0.88, demonstrating the model's relatively high ability to predict changes. Comparing the land use maps for 2033, 2043, and 2053 with the land use map for 2023, it was determined that over the next three decades, urban land use would increase by 45.9%, 46.9%, and 47.5%, and rangeland would increase by 10.9%, 7.6%, and 4.5%, respectively. In contrast, irrigated agriculture would decrease by 27.9%, 21.1%, and 14.9%, and dryland agriculture would decrease by 13.4%, 11.23%, and 9.3%, respectively. https://gisj.sbu.ac.ir/article_106153.html Introduction: Crop growth models are convenient tools for understanding and predicting the interactions between crop growth, environmental conditions, and land management practices such as irrigation (Servin-Palestina et al., 2022; Li et al., 2023). The crop models comprise several computational stages and parameters along with climate, soil, crop, management, temperature, salinity, fertility, and water stress conditions (Akbari et al., 2024b). These factors can significantly challenge model calibration, even potentially leading to uncertainties in the results (Guo et al., 2019). To successfully run a crop simulation model, the selected model needs to be calibrated with accurate crop model parameters based on local soil conditions, weather, management practices, and other conservative/non-conservative parameters that may be difficult to measure locally (Shan et al., 2021). To address this challenge, it demands a spatially explicit data assimilation strategy that incorporates the observed data to calibrate the model parameters. It minimizes the difference between observed data and the state variables simulated by the crop growth model and then estimates the model parameters (Hoefsloot et al., 2012). The assimilation of the satellite-derived products and their spatial variability as pixels in each farm into such models can, to some extent, resolve the uncertainties introduced by the assumption of homogeneity in croplands (Hoefsloot et al., 2012; Jin et al., 2017). Calibrating a crop growth model for the specific location and agricultural conditions of a region can thus be a powerful tool for developing effective water management strategies that enhance production while minimizing water consumption (Hsiao et al., 2009). Furthermore, when calibrating crop growth models on a spatial scale beyond an individual farm, it is necessary to reduce the uncertainties related to input data to account for the lack of information about land management and the structure of the model. To cope with these limitations (e.g., data scarcity, uncertainty), the pragmatic practice seeks to simplify crop growth models with fewer parameters and data requirements. It is therefore necessary to determine the minimum number of effective parameters in each of the crop growth models to achieve a more accurate and optimal model calibration, or, in other words, apply a sensitivity analysis (SA) (Silvestro et al., 2017). Material and methods: This study examines the critical role of sensitivity analysis (SA) in model parameter calibration as a part of assimilating satellite data into crop growth models with the purpose of improving the accuracy of crop growth simulations and yield estimation. Calibration involves adjusting model parameters with the purpose of minimizing discrepancies between observed variables and model simulations. Undoubtedly, the choice of the calibration method for optimizing crop model parameters depends on the specific model and requires knowledge of its most influential and sensitive parameters, as can be defined by SA. In this light, aiming for optimizing assimilation of data streams of satellite products in crop growth modeling, it is indispensable to identify the most sensitive model parameters and those that can be fixed. Restricting input parameters reduces redundancy and uncertainty, particularly when calibrating models for specific study sites. This review explores the diversity of SA techniques applicable to crop growth models, aiding readers in choosing the best SA method for their needs.Results and discussion: The study reveals that global SA methods are predominantly employed in crop growth model calibration practices, especially when data streams of satellite products have been assimilated into the model. As a general trend in the reviewed studies, the EFAST model tends to outperform Sobol in use and accuracy. In cases where complexity is high, it is suggested to use the Morris method for screening parameters in combination with applying the EFAST model to reduce computational complexity and crystallize the most effective parameters at relatively high accuracies. Furthermore, this review study shows the ensemble, i.e., combination, of global SA methods Morris and EFAST outperforms other SA methods in calculation efficiency and in precision of identifying driving parameters. Such ensemble strategies excel in finding the driving parameters, which can lead to fine-tuned calibration and, in turn, to more precise crop growth model simulations. Conclusion: We conclude that an ensemble of global SA methods is an appropriate choice for overcoming the challenges and limitations of each technique and reducing the computational complexities when introducing satellite data assimilation into common crop growth models. https://gisj.sbu.ac.ir/article_106299.html Land is a fundamental and finite resource that supports the physical development of various sectors, including agriculture, housing, industry, mining, and transportation. As population growth accelerates, the demand for land increases accordingly, leading to a dynamic competition among different land use types. This condition contributes significantly to the transformation of land use and land cover (LULC), especially in rapidly developing areas. These transformations often involve the conversion of productive agricultural land into non-agricultural uses, raising concerns over long-term food security, ecological sustainability, and spatial equity. Majalengka Regency, located in West Java Province, Indonesia, has become one of the most dynamic regions in terms of land transformation due to its inclusion in the national development strategy through the Rebana Triangle Special Economic Zone (SEZ). This strategic zone, connecting Cirebon, Patimban, and Kertajati, is envisioned to accelerate industrial growth, infrastructure development, and regional connectivity. Within this framework, Majalengka plays a critical role, particularly with the construction of West Java International Airport (BIJB) and the surrounding industrial corridors. While these developments offer promising economic potential, they also exert significant pressure on existing land resources, particularly agricultural areas such as rice fields and drylands. The objective of this study is to analyze spatial and temporal changes in LULC across Majalengka Regency over a ten-year period from 2011 to 2021. The research utilizes multispectral remote sensing data from the Sentinel-2A satellite, which provides high temporal resolution and medium spatial resolution suitable for regional-scale analysis. The image data were processed using the Google Earth Engine (GEE), a cloud-based geospatial analysis platform that enables efficient access, processing, and analysis of large satellite datasets without requiring local storage or high-end computing infrastructure. GEE's capability to conduct multi-temporal analysis over extended periods makes it a valuable tool for environmental monitoring and spatial planning. Land cover classification was conducted using the Smile-Random Forest (RF) algorithm, a supervised machine learning approach known for its accuracy in handling multidimensional remote sensing data. To improve the accuracy and thematic detail of the classification, two additional spectral indices were incorporated: the Normalized Difference Built-Up Index (NDBI) and the Normalized Difference Water Index (NDWI). These indices enhanced the model’s ability to distinguish between built-up areas, water bodies, and vegetated or agricultural land. Furthermore, base maps of rice field distribution were integrated into the classification process to refine the delineation of agricultural zones, particularly paddy fields that are crucial to local food systems. The classification model achieved high levels of accuracy, with an Overall Accuracy (OA) of 98.81% and a Kappa coefficient of 95.91%, indicating a strong level of agreement between predicted and ground truth data. The spatial analysis revealed a considerable decline in agricultural land over the ten-year period, with a net reduction of approximately 4,457.36 hectares in rice fields and drylands. Conversely, there was a marked increase in built-up land, including residential settlements, industrial areas, and transportation infrastructure associated with the expansion of BIJB and its surrounding economic zones. These findings underscore the complex relationship between regional development initiatives and environmental sustainability. The ongoing land conversion, if left unregulated, poses risks to agricultural productivity, local food security, and ecological resilience. The study emphasizes the need for integrated land use planning and policy interventions that balance economic growth with the conservation of essential land resources. Spatial planning efforts must be aligned with long-term sustainability goals, particularly in regions that are designated for strategic economic development. Moreover, this research highlights the utility of combining remote sensing technology, spectral indices, machine learning algorithms, and cloud-based platforms as an efficient and scalable methodology for monitoring land use change. The use of GEE significantly reduces processing time and technical barriers, allowing for real-time analysis and easy replication in other regions facing similar developmental pressures. In conclusion, this study provides a comprehensive assessment of land use changes in Majalengka Regency within the context of rapid economic transformation. The methodological framework presented here offers practical implications for policymakers, planners, and environmental managers in designing land governance strategies that are data-driven, forward-looking, and sensitive to both developmental and environmental dimensions. https://gisj.sbu.ac.ir/article_106303.html Background and Objective: One of the environmental challenges in arid and semi-arid regions is dust pollution, which can lead to serious health problems, including respiratory diseases, reduced visibility, and disruptions in transportation. Additionally, dust storms have significant negative impacts on water resources and agriculture. Sistan and Baluchestan province is one of the areas that experiences high dust pollution levels annually, with many periods throughout the year showing elevated dust pollution levels.Materials and Methods: This study utilizes MODIS satellite data and coding in Google Earth Engine to analyze the TDI, AOD-Sum, AOD-Max, and AOD indices from 2018 to 2023. The HYSPLIT model was employed to analyze the transport pathways of dust pollutants and identify their sources. Using particle trajectory modeling techniques, the frequency distribution of closed air paths was examined. To gain a better understanding of dust distribution and transport, true-color MODIS images were also used. For dust trajectory analysis, data from the Zabol and Zahedan stations for three dates in 2023 and 2024, with an AQI index of 500, were employed. The HYSPLIT model was applied in a backward mode with 24-hour trajectories for Zabol and 48-hour trajectories for Zahedan.Results and Discussion: The analysis of the Thermal Dust Index (TDI) from 2018 to 2023 revealed that areas such as Zabol, Iranshahr, Khash, and Chabahar, due to their dry and loose soils, are the primary internal sources of dust in the province. The TDI increased from 0.0055 in 2018 and 2019 to 0.0058 in 2021, while in 2022 and 2023 it reached 0.0056 and 0.0057, respectively, with a minimum threshold of 0.018. The analysis of the AOD-Max index indicates that the eastern, southern, northeastern, southwestern, and, in some years, the central regions of the province experience the highest levels of dust pollution. Border regions, especially those bordering Afghanistan and Pakistan, have consistently exhibited the highest levels of dust pollution throughout the years. The years 2018 and 2022 recorded the highest values of AOD-Max, with a 0.3-unit increase in 2022 compared to previous years, reaching a value of 3.5, which falls into the "hazardous" category in air pollution classification. This value decreased to 3.1 in 2023 but remained in a "very hazardous" state. The AOD-Sum index analysis shows that the eastern, northeastern, and southern regions of Sistan and Baluchestan experience the highest intensity of dust pollution throughout the year. Particularly, the eastern and northeastern areas face dust pollution for more than 100 days a year, while the southern areas experience it for over 120 days. The highest number of pollution days were observed in 2018, 2020, and 2022. However, the average index value for 2023 decreased by 0.9 compared to 2022, with an average of 1.9, still within the hazardous range. The analysis of AOD indices reveals that the highest pollution is concentrated in the border regions of the province. Moreover, the strong spatial correlation between TDI and AOD values reinforces the validity of these findings and demonstrates that TDI serves as an effective tool for identifying, monitoring, and managing high-risk dust-prone areas. Backward trajectory modeling with the HYSPLIT model shows that, shortly before dust storms occur in Zabol and Zahedan, the air paths predominantly pass through the borders of Turkmenistan and Afghanistan, reaching Zabol and Zahedan. The backward trajectory modeling shows that dust storms originate from the deserts of Turkmenistan and Afghanistan and reach Zabol within 24 hours and Zahedan within 48 hours. The altitude changes of the dust transport pathways indicate that most of the airflows occur at elevations above 1500 meters along the Turkmenistan-Afghanistan border. After passing through the deserts of Afghanistan, the airflow reduces to below 500 meters, causing dust pollution in the province. The true-color MODIS images also clearly show the expansion of pollution from the deserts of Afghanistan and eastern Iran to the borders of Pakistan.Conclusion: The results show that the eastern and border regions of Sistan and Baluchestan province are most affected by dust storms. These storms, primarily originating from the deserts of neighboring countries Afghanistan, Turkmenistan, and Pakistan—enter the province and exacerbate air pollution. Given the severity of dust pollution in these areas, it is recommended to establish drought-resistant vegetation cover, https://gisj.sbu.ac.ir/article_106304.html ABSTRACTIntroduction: In recent years, with increasing pressure on natural resources and the need for sustainable use of agricultural land, precision agriculture has gained growing importance as an efficient approach for smart resource management. One of the fundamental challenges in this field is the accurate identification of crop types and monitoring their growth stages at appropriate temporal and spatial scales. Remote sensing technology, particularly Synthetic Aperture Radar (SAR), enables the extraction of precise ground information under various weather conditions. Unlike optical data, which are highly dependent on illumination and often limited in cloudy regions, radar datasuch as Sentinel-1 imagery provide effective tools for agricultural monitoring with their all-weather, day-and-night imaging capability. In this context, the present study aims to investigate the potential of Sentinel-1 radar time series data and its VV and VH polarizations, along with derived polarimetric indices, for accurate crop classification in an agricultural area located in the suburbs of Mashhad. The main focus of this research is to evaluate the capability of different machine learning algorithms combined with radar data to enhance classification accuracy and achieve more precise crop identification.Materials and Methods: For this study, Sentinel-1 radar time series data with VV and VH polarizations, covering the period from winter 2021 to spring 2022, were used. The study area includes agricultural lands in Mashhad County, characterized by a variety of crops such as wheat, chickpea, alfalfa, as well as non-cropland areas. Through radar data processing, four key polarimetric indices NRPB (Noise-to-Backscatter Ratio), DPDD (Dual-Polarization Difference), IDPDD (Integrated Dual-Polarization Differential), and VDDPI (Temporal Variation Index for VV and VH) were extracted and employed in combination with the original data for classification purposes.Three powerful machine learning algorithms XGBoost, Random Forest (RF), and Support Vector Machine (SVM) were applied for crop classification. Training samples were collected for seven defined classes within the study area, and classification accuracy was evaluated using the error matrix, Kappa coefficient, and overall accuracy.Results and Discussion: The results of modeling and classification, which were validated using field data associated with the coordinates of each plot, showed that the XGBoost and RF algorithms performed significantly better than the SVM algorithm. The overall accuracy and Kappa for the XGBoost model were 83.48% and 0.78, respectively, and for the RF model were 82.27% and 0.78, whereas the SVM algorithm achieved an overall accuracy and Kappa of 61.46% and 0.51. This performance difference is primarily attributed to the superior ability of tree-based algorithms to model complex and nonlinear relationships between features and classes.Among the polarimetric indices, DPDD and IDPDD demonstrated distinct temporal behaviors during different crop growth stages, proving highly valuable for phenological crop discrimination. Crops such as alfalfa, chickpea, and wheat were classified with higher accuracy and less confusion by XGBoost and RF, whereas SVM struggled to separate classes with similar vegetation cover, leading to substantial overlaps between certain crop types. Among the polarimetric indices, DPDD and IDPDD demonstrated distinct temporal behaviors during different crop growth stages, proving highly valuable for phenological crop discrimination. Crops such as alfalfa, chickpea, and wheat were classified with higher accuracy and less confusion by XGBoost and RF, whereas SVM struggled to separate classes with similar vegetation cover, leading to substantial overlaps between certain crop types.Conclusion: This study clearly demonstrated that Sentinel-1 radar data particularly VV and VH polarizations combined with time-series derived polarimetric indices, hold strong potential for accurate crop classification. The integration of these data with advanced machine learning algorithms, especially XGBoost and RF, can provide reliable alternatives to traditional optical-based methods, particularly in cloudy regions or areas with limited access to optical data. Moreover, the findings, in line with similar international studies, highlight the importance and effectiveness of polarimetric indices as key tools for periodic crop monitoring. Utilizing these indices alongside time-series data represents a significant step toward optimizing agricultural land management, enhancing productivity, and promoting sustainable development in the agricultural sector. Consequently, the adoption of modern remote sensing technologies and machine learning will play a pivotal role in shaping the future of smart and sustainable agriculture. https://gisj.sbu.ac.ir/article_106305.html Introduction: Place names, a common form of embedded geographic information in natural language texts, are used in various resources such as social media, news stories, historical archives, and property listings. The names are presented in different forms like business addresses, hashtags, or simple texts. Providing up-to-date data, carrying human experience and cognition, and containing types of geospatial information only available in tex-tual resources make these resources precious for geospatial analyses. Therefore, mapping place names to their footprints is an essential task. One of the solutions for this task is using a digital gazetteer, a dictionary of place names. These precious resources enable Geographic Information Retrieval (GIR) systems to detect place names (geotagging) and convert the candidate ones to their geographic coordinates (geocoding). To fulfill ever-increasing geospatial demands, especially in GIR and LBSs, digital gazetteers should be enriched.Materials and Methods: This paper presents a three-tier framework to extract urban geographic information from geotagged housing listings. The first tier is devoted to harvesting main street and neighborhood place names, which the authors usually write without any linguistic clue due to their well-knownness. Using a random forest model based on a set of spatial measures for each extracted n-gram from the textual content of real estate advertisements enables us to identify the main streets and neighborhoods. The first tier commences with the ex-traction of n-grams from the saved advertisements. After cleaning and standardizing the n-gram set, spatial clus-tering is applied, considering that each spatial n-gram can refer to multiple regions of the city. The defined spa-tial predictors are computed for each not-clustered n-gram or split n-gram from its generic cluster. Subsequent-ly, a random forest model identifies the neighborhood and the main street n-grams. We developed a rule-based model to extract all urban place names in the second tier and a linguistic pattern-based model to extract spatial relationships in the third tier. This research focused on the Persian language and Tehran, Mashhad, Isfahan, and Shiraz metropolises from Iran as study regions.Results and Discussion: The results are encouraging for the first tier, specifically achieving approximately 0.8 and 0.7, respectively, for recall and precision in predicting another metropolis’s main streets and neighborhoods. However, differences in population levels and urban development patterns decreased the performance in identi-fying a neighborhood as a main street or vice versa. For the second tier, precision and recall are near 0.7. Alt-hough these results are notable compared to the performance of named entity recognition models in extracting urban place names which are often fine-grained, errors in this layer have led to reduced precision and recall in the third layer, spatial relation extraction.Conclusion: Gazetteers are important geospatial resources in GIR tasks, especially in geoparsing. This paper presented a framework for extracting urban geographic information from online property listings. This geo-graphic information includes the place names and the spatial relationships to enrich current gazetteers. Since main streets and neighborhoods as a part of place names are well-known, people mainly use them without any clue on property listing websites. Harvesting these place names can be done using a machine learning-based model. The next step is extracting all place names written in the property advertisement posts. To realize that, we developed a rule-based model to extract potential place names from the posts geographically located in the neighborhood/main street place name’s convex-hull and remove the wrong identified cases. In the third step, we extracted spatial relationships between the place names extracted from each post text based on linguistic patterns. The framework has provided good results in harvesting main streets and neighborhoods and extracting place names. Extracting spatial relationships between the place names needs further work. https://gisj.sbu.ac.ir/article_106306.html IntroductionIn recent decades, the Hamoun Lakes have almost dried up due to drought and unsustainable management of water resources (construction of dams, expansion of agricultural lands and systematic diversion of water). This issue, considering the importance of these lakes in the Sistan region, has caused many environmental and socio-economic challenges, including dust storms in this region. Therefore, it seems necessary to study the changes of water areas and their effects on the surrounding environment. Accordingly, the forecasting/projection of the future perspective of land use/cover (LULC) changes is considered as one of the key and fundamental tools for planning and sustainable management of territorial resources and decision-making to address the resulting challenges. In this regard, the literature shows that the use of multispectral remote sensing satellite imagery has found widespread use due to its wide spatial-temporal coverage and lack of dependence on costly field work. Various approaches have been used to model LULC changes and project future trends, among which the results of the CA-Markov model are more reliable. Despite the many studies that have been conducted to monitor LULC changes in the Hamoun Lakes, their focus has mostly been on agriculture and vegetation classes, and the issue of lake drying and its different dimensions have not been well understood. On the other hand, considering the rapid changes of the Hamoun lakes in the last two decades, it seems that we should focus on projecting the state of the lakes in the near future, which has not been given much attention in previous studies.MethodologyThe main objective of this study is to forecast the changes in the water areas of Hamoun Lakes located in southeastern Iran. For this purpose, the Landsat 5-TM and Landsat 8-OLI images were used for the years 1991 and 2022, respectively. Initially, the support vector machine (SVM) classifier was used to produce LULC maps for these years. The main advantage of SVM is its ability to solve complex classification problems with a large number of features and few training samples, making it a suitable option for classifying remote sensing images. Then, the changes in the water areas of the Hamoun Lakes for the year 2030 were forecasted taking advantage of the CA-Markov model. The CA-Markov analysis is a suitable tool for modeling LULC changes.Results and discussionThe SVM classifier gave the best performance for the Radial Basis Function (RBF) kernel. This kernel has the highest (maximum 98.3%) and lowest (minimum 86.3%) intra-class accuracy in detecting water body and built-up classes, respectively, in the years studied. Achieving an overall classification accuracy of more than 93% for the RBF kernel indicates the acceptable performance of the SVM classifier and the reliability of its results. The findings show that the area of lakes and wetlands in the region has decreased by 88% and 94%, respectively, in 2022 compared to 1991. During the study period, the area of salty lands has almost doubled, and the greatest loss of area corresponds to water and vegetation classes that have been transformed into this class. Forecasting of the LULC changes using the CA-Markov model indicates that in less than the upcoming decade, water areas including Hamoun Puzak and Saberi lakes and wetlands will become completely dried up and transformed into salty lands.ConclusionThe very high rate of LULC change in the study area indicates the very critical situation of the region in terms of the loss of water and plant resources and the expansion of desert lands. Therefore, it is necessary to focus on the near future and target setting to achieve sustainable territorial management in this region based on short-term time horizons with high priority. In general, the results of the current research emphasize the critical situation of the surface water resources in the study area and the need for special attention to manage the resulting problems. https://gisj.sbu.ac.ir/article_106369.html Introduction: Wind erosion is one of the most serious environmental issues in the world. The most important effects resulting from wind erosion include the formation of wind deposits, sparsity of vegetation cover, changes in soil texture, reduction of soil fertility, land degradation, and air pollution. Studying of wind erosion is one of the effective steps in the managing and control of this phenomenon. In this regard, the tools that have become importance for identifying and monitoring of wind erosion include remote sensing technology and artificial intelligence, which is designed based on numerous algorithms. The aim of this study is to identify and monitor areas susceptible and sensitive to wind erosion using Landsat satellite imagery, machine learning technology, and the Random Forest algorithm over the years 2013 to 2023 in the study area.Materials and Methods: In this study, three remote sensing indices-including the Soil Adjusted Vegetation Index (SAVI), the Normalized Difference Moisture Index (NDMI), and the Land Surface Temperature (LST) index, were used for the identification of areas sensitive to wind erosion during the period from 2013 to 2023. In this regard, Landsat 8 satellite images and OLI sensor data from the month of June were used. For the identify and monitor areas susceptible to wind erosion, the machine learning method and the Random Forest (RF) algorithm were utilized. The wind erosion assessment resulting from the Random Forest algorithm was classified into four classes: low, moderate, severe, and very severe. Additionally, the Random Forest algorithm also showed the relative importance of input indices for identifying areas susceptible to wind erosion during the 2013-2023 period. The accuracy and validation of the Random Forest algorithm model were determined using statistical indices: coefficient of determination (R²), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Area Under the ROC Curve (AUC).Results and Discussion: The results of the wind erosion assessment in the 2013-2023 period showed that the SAVI index increased from 2013, with maximum values of 0.78 and minimum values of -0.41, to 2018, with maximum values of 0.79 and minimum values of -0.09. From 2018 to 2022, the amount of vegetation cover showed a significant decrease, with maximum values of 0.00015 and minimum values of -0.00005. The NDMI index from 2013 with a maximum value of 0.91 and a minimum value of -1, to 2016 with a maximum value of 0.51 and a minimum value of -0.99, indicates a decreasing trend in surface soil moisture. From 2016 to 2018, with a maximum value of 1 and a minimum of -0.77, it indicated an increasing trend in surface soil moisture. Also, from 2018 to 2023, with maximum values of 0.84 and a minimum of -1, it indicates a decreasing trend in soil surface moisture. The LST (Land Surface Temperature) index also fluctuated between 2013 and 2023, based on vegetation cover and soil surface moisture indices. The most critical status in terms of wind erosion was estimated to be in the year 2022, with an area of 3,530,221 hectares (99.86%) classified as very severe. The validation results of the Random Forest algorithm for identifying areas susceptible to wind erosion in the study area during the years 2013 to 2023 showed that the Correlation coefficients (R2) were estimated to be between 0.4 and 0.87, the Root Mean Square Error (RMSE) between 0.022 and 0.069, the Mean Square Error (MSE) between 0 and 0.0048, and the Area Under the ROC Curve (AUC) value to be greater than 0.923. The results indicate the high efficiency of the Random Forest algorithm for identifying areas sensitive to wind erosion in the study area. The SAVI index was found to be one of the most effective indices examined for wind erosion in the study area.Conclusion: The results indicate that the year 2022 was found to be the most critical year in terms of the wind erosion phenomenon, classified as very severe. The influential factors on wind erosion during the years 2013 to 2023 are the status of vegetation cover and surface soil moisture. In this research, the information obtained from the monitoring and identification of erosion-susceptible areas can be utilized for project planning, with the aim of managing and controlling wind erosion in the study area. https://gisj.sbu.ac.ir/article_106370.html Background and Objectives: Monitoring greenhouse gases, particularly methane, is of great importance due to its impact on climate change and global warming. Methane, after carbon dioxide, is the second most significant greenhouse gas resulting from human activities. Due to its high ability to absorb and retain heat, methane plays a crucial role in increasing global temperatures. Studies indicate that over a 20-year period, methane's warming effect is approximately 84 times greater than that of carbon dioxide. Therefore, identifying emission sources and accurately monitoring methane at local, regional, and global scales is essential for developing effective strategies to mitigate climate change. There are two main approaches to methane monitoring: the bottom-up method, which relies on local measurements and emission inventories, and the top-down method, which is based on remote sensing and inverse modeling. The top-down method, utilizing remote sensing technologies such as satellite and airborne sensors, enables the identification and analysis of methane concentrations on large scales. This method is particularly valuable in areas where ground-based data is insufficient. In this study, remote sensing technologies used for methane monitoring, including thermal infrared sensors, shortwave infrared spectroscopy, and LiDAR, are examined, and their advantages and limitations are analyzed. Materials and Methods: The aim of this study was to investigate methane monitoring methods through top-down approach and remote sensing data. For this purpose, extensive library studies have been conducted to identify different technologies of satellite and airborne sensors. These technologies include thermal infrared, shortwave infrared, and lidar sensors. In this study, the combination of data obtained from different sensors has been investigated in order to improve the accuracy and reduce the uncertainties associated with each method. Results and Discussion: The results of this study show that remote sensing technologies, particularly shortwave infrared and LiDAR, are powerful tools for large-scale methane monitoring. Thermal infrared and shortwave infrared sensors, due to their high spectral sensitivity, can identify and measure methane concentration in the atmosphere. However, they face challenges such as spectral interference of methane with other atmospheric gases, including water vapor and carbon dioxide, which affect measurement accuracy. On the other hand, LiDAR, due to its ability to provide three-dimensional data and directly measure methane concentration, offers higher accuracy compared to other remote sensing methods. However, its high cost and the need for advanced equipment are among the limitations of this method. One of the main challenges in using these technologies is the spatial and temporal resolution limitations of satellite sensors. Although these sensors enable large-scale methane monitoring, they face difficulties in detecting point-source emissions, such as small gas leaks from oil and gas facilities. Environmental and atmospheric barriers also pose challenges in methane monitoring using remote sensing. Cloud cover, aerosols, and atmospheric water vapor can absorb and scatter radiation in infrared bands, reducing measurement accuracy. Additionally, inconsistencies in inverse modeling parameters, such as atmospheric temperature and pressure, can increase systematic errors in estimating methane concentration. To mitigate these challenges, the integration of multi-source data from satellite, airborne, and ground-based sensors has been proposed. Conclusion: Methane monitoring using the top-down approach and remote sensing data, particularly through satellite and airborne systems, plays a crucial role in global surveillance of methane emissions and assessing its impact on climate change. Technologies such as shortwave infrared, thermal infrared, and LiDAR allow for the identification of emission sources, estimation of methane concentration, and large-scale monitoring. However, these methods face challenges such as spatial and temporal resolution limitations, susceptibility to atmospheric conditions, and complexities in data modeling. The development of more advanced sensors, improvements in radiative transfer models, and the integration of machine learning-based technologies in remote sensing data processing can help reduce these challenges and enhance the accuracy of methane monitoring. Ultimately, the combination of multi-source data from satellite, airborne, and ground-based sensors, along with improved data analysis algorithms, can enhance monitoring accuracy, improve emission source identification, and provide more precise estimates of methane emissions. https://gisj.sbu.ac.ir/article_106466.html AbstractIntroduction: Snow cover is among the most critical natural resources influencing water availability, surface runoff, agriculture, and tourism, with significant implications for both natural and human systems. Climatic signals often exert considerable influence on various meteorological elements, particularly snow cover during and after precipitation events. The impact of climate variability on snow accumulation and melt dynamics plays a pivotal role in the management of water resources in river basins that rely on snowmelt for their hydrological regimes. Accordingly, the present study aims to analyze the behavior of snow cover in the Karun River Basin and its relationship with climatic signals over a 22-year statistical period (2001–2022).Materials and Methods: Initially, validated snow cover products derived from the MODIS sensor—specifically the Normalized Difference Snow Index (NDSI)—were retrieved within the Google Earth Engine (GEE) platform, spatially aligned with the Karun River Basin. Subsequently, time series data for 29 teleconnection patterns known to influence the climate of Iran and the target basin were compiled for the study period. To assess the trend and magnitude of snow cover changes, the non-parametric Mann–Kendall test and Sen’s slope estimator were employed. Furthermore, Pearson correlation analysis was conducted using SPSS software to evaluate the statistical relationships between snow cover data and the teleconnection indices.Results and Discussion: The findings of this study indicate a declining trend in snow cover across the Karun River Basin during the cold months of the year, accompanied by statistically significant negative shifts. Specifically, during January, February, March, April, November, and December, the snow cover exhibited a consistent downward trend with abrupt reductions throughout the study period. The output of the Sen’s slope estimator further revealed a total decrease of approximately 2,794 square kilometers in snow-covered area. Correlation analysis between snow cover extent and teleconnection indices demonstrated that snow cover is significantly influenced by several atmospheric–oceanic patterns. At the 0.05 significance level, simultaneous negative correlations were observed with indices such as GMSST (February), EAWR (March), SOI, and RMM2 (December). During the cold season (November to May), snow cover also showed significant delayed correlations (one-month lag) with Solar Flux, EA, AAO, EAWR, RMM2, and SOI. Additionally, at the 0.01 significance level, a strong negative correlation was found with the AMO index in November.Conversely, significant positive correlations at the 0.05 level were identified between snow cover and indices including EAWR, EPNP, SCA, PBO, OSI, NINO3.4, NINO4, ONI, and PNA. During the cold season (November to May), positive associations were also evident with SOI, MEIv2, ESPI, and EPO. At the 0.01 level, snow cover exhibited strong positive correlations with the SCA index (May) and ENSO-related indices (ONI, NINO3.4, NINO4, MEIv2, ESPI, and NINO3.1), particularly in December. Overall, the highest observed correlations were associated with various ENSO indices and teleconnection patterns such as EAWR, MEIv2, and the Southern Oscillation Index (SOI). These results suggest that both synchronous and lagged fluctuations in selected teleconnection patterns have statistically significant relationships with snow cover variability in the Karun Basin. Given the predictability of these large-scale climate signals and their strong correlations with snow cover dynamics, they offer valuable potential for improving future snow cover forecasts in the region.Conclusion: Based on the results of this study during the 2001–2022 period, it was determined that snow cover in the Karun River Basin, located in the southern Zagros region, has been undergoing a declining trend. Moreover, fluctuations in several of the examined teleconnection patterns—across both their positive and negative phases—were found to exert synchronous and lagged influences on the extent of snow cover in the basin. These influences manifested as either reductions or increases in snow-covered area, depending on the phase and timing of the respective climate signals. Given the relative predictability of the examined teleconnection patterns, it is recommended that future studies incorporate advanced modeling approaches such as machine learning and deep neural networks. The application of these techniques can enhance the accuracy of estimating fluctuations in teleconnection indices and, consequently, improve the forecasting of snow cover variability in the Karun River Basin. https://gisj.sbu.ac.ir/article_106538.html AbstractBackground and Objective: Groundwater drought, defined as the persistent deficit in groundwater storage, is a major subcategory of hydrological drought that directly affects drinking water, irrigation, and industry. The Central Plateau of Iran faces chronic water stress due to climate variability and increasing demand. This study evaluates groundwater drought conditions and the long-term trend of groundwater storage anomalies (GWSA) across the Central Plateau basins using the G3P satellite product, based on GRACE/GRACE-FO gravity data with a spatial resolution of 0.5° and monthly coverage from April 2002 to September 2023. Employing the new G3P product can reduce field monitoring costs and, instead of relying on limited observational data, provide a more comprehensive picture of groundwater status. The Central Plateau is facing a severe water crisis due to both climate change and declining available water resources on one hand, and population growth with increasing demand on the other. Considering the key role of groundwater resources in supplying drinking water, agriculture, and industry in this arid and semi-arid region, precise assessment of their changes is of critical importance.Materials and Methods: Groundwater variations were analyzed using G3P satellite data, retrieved from the G3P Data Portal for the period 16 April 2002 to 16 September 2023. G3P data are derived from GRACE and GRACE-FO satellite gravity observations and provided monthly with a spatial resolution of 0.5° (~50 km). By integrating field and reanalysis datasets such as GLDAS, G3P estimates surface water storage components—including soil moisture, surface water, snow and ice, and vegetation—then calculates groundwater volume using the water balance equation. Python and Excel were used to process GWSA and the Groundwater Drought Index (GDI). In this study: (1) basin-averaged GWSA time series (in millimeters of water equivalent) and (2) the GDI, based on normalization of monthly anomalies relative to the reference climatology, were calculated to determine the onset, duration, and severity of groundwater drought.Results and Discussion: The Central Plateau basins of Iran exhibited a significant negative trend in both GWSA and GDI during 2002–2023. The decline intensified from around 2011 and worsened after 2016. Spatially, the most pronounced decreases occurred in southern and central sub-basins such as Abarkooh–Sirjan, Tashk–Bakhtegan–Maharloo, and the Darreh Anjir desert, as well as in the provinces of Yazd, Kerman, Isfahan, and northern Fars. In contrast, northern sub-basins (Semnan, Tehran, and parts of Khorasan) showed milder negative trends. Seasonally, deficits were most notable from late winter through spring, aligning with precipitation patterns and peak withdrawal periods. The GDI confirmed recurrent and prolonged groundwater drought episodes in the past decade. Months of January, February, March, April, May, June, and December exhibited negative trends, with February (–66.81 mm), March (–65.78 mm), and January (–54.76 mm) recording the steepest declines. Among the basins, the Salt Lake watershed showed the lowest decline (–2.21 mm), while Abarkooh–Sirjan experienced the steepest decrease (–22.21 mm) during the study period.Conclusion: Groundwater storage across the Central Plateau of Iran has declined continuously since 2002 and has intensified markedly since 2016. The absence of any sustained positive trend highlights a prolonged crisis of groundwater depletion, particularly in the southern and central basins. Routine use of satellite-based GWSA offers cost-effective, basin-scale monitoring to support early drought warning and strategic water resource planning in data-scarce environments. The findings demonstrate that all regions of the Plateau are experiencing persistent groundwater decline, with the most severe reductions in Yazd, Kerman, Isfahan, and northern Fars, while northern regions such as Semnan, Tehran, and parts of Khorasan also show decreasing trends, albeit less severe. The Abarkooh–Sirjan, Tashk–Bakhtegan–Maharloo, and Darreh Anjir basins are facing the steepest declines.Keywords: Groundwater storage, drought, watershed, Central Plateau of Iran, G3P https://gisj.sbu.ac.ir/article_106546.html ABSTRACTBackground and objectives:Zoonotic cutaneous leishmaniasis (ZCL), one of the most significant vector-borne parasitic diseases, poses a major public health challenge in many semi-arid and warm regions of the world, particularly in the Middle East and Iran. The disease follows a distinct spatiotemporal pattern that is strongly influenced by environmental and ecological factors such as temperature, vegetation cover, and soil moisture. In recent years, climate change, habitat degradation, and the expansion of human settlements into environmentally sensitive areas have altered the distribution of vectors and reservoir hosts, thereby increasing the risk of emergence and expansion of new transmission foci. Consequently, anticipatory estimation of future disease risk plays a critical role in designing targeted interventions, optimizing resource allocation, implementing preventive planning, and establishing early-warning systems. The present study aimed to predict the spatiotemporal risk of ZCL in Ilam Province, western Iran, up to the year 2030, using simulated remote-sensing data and available epidemiological records.Materials and methods:In the initial phase, a total of 5,353 reported ZCL cases from 2014 to 2019 were subjected to data cleaning, quality control, and georeferencing procedures to construct a baseline disease-intensity map within a Geographic Information System (GIS) framework. This map served as the primary epidemiological layer reflecting the historical spatial distribution of the disease. Subsequently, three key environmental predictors—Soil-Adjusted Vegetation Index (SAVI), Land Surface Temperature (LST), and Soil Moisture Index (SMI)—were derived from Landsat-8 imagery for the 2014–2024 period, using the Google Earth Engine platform. Pixel-wise time series spanning ten years were analyzed through linear regression to characterize temporal trends for each variable. Based on these trends, pixel-level values were extrapolated to 2030, and simulated future environmental layers were generated. The cumulative epidemiological surface and the projected ecological layers were then integrated as input features within a Support Vector Machine (SVM) framework to produce a spatially explicit ZCL risk-prediction model for 2030. Model performance was rigorously assessed using multiple statistical metrics, including the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Area Under the Receiver Operating Characteristic Curve (AUC), Cohen’s Kappa coefficient, overall accuracy, and k-fold spatial cross-validation. Furthermore, a model-uncertainty map was constructed based on the standard deviation of ensemble predictions and visualized as an independent spatial layer.Results and discussion:The results demonstrated that the proposed framework exhibits a high capability in capturing and representing the spatiotemporal patterns of ZCL risk. The SVM model achieved reliable performance (RMSE ≈ 18.9, MAE ≈ 7.5, AUC ≈ 0.81, Kappa ≈ 0.68, and an overall accuracy of approximately 0.91), indicating strong discriminative power between high-, moderate-, and low-risk areas. The risk map projected for 2030 revealed a higher concentration of risk in the dry, warm, and low-altitude regions of the southern and western parts of Ilam Province, whereas the higher-elevation and mountainous regions in the northern, central, and eastern parts were predominantly classified as low-risk zones. Co-location analysis between environmental layers and the risk map indicated a significant association between increasing land surface temperature, decreasing vegetation greenness, reduced soil moisture, and the intensification and expansion of high-risk areas. Furthermore, the uncertainty map demonstrated relatively low levels of uncertainty in most critical zones, with slightly higher values in marginal and transitional areas, confirming the robustness and stability of the model predictions.Conclusion:The findings of this study indicate that integration of simulated remote-sensing data, spatial epidemiological information, and advanced machine-learning algorithms provides a powerful, efficient, and generalizable framework for predicting the future risk of zoonotic cutaneous leishmaniasis in endemic regions. The projected expansion of high-risk clusters toward the southern parts of Ilam Province by 2030 highlights the urgent need for continuous environmental monitoring, targeted interventions in critical hotspots, and the development of climate-adaptive preventive strategies. The proposed framework can serve as a scientific foundation for establishing intelligent monitoring and early-warning systems for environmentally driven diseases and can play a significant role in supporting data-driven policymaking, optimized resource management, and the enhancement of public-health resilience. https://gisj.sbu.ac.ir/article_106547.html Introduction: Nowadays, satellite imagery enables the classification of land cover, which is one of the key approaches in analyzing environmental changes, managing natural resources, assessing land use dynamics, and monitoring natural hazards. These methods assist urban planners, land resource managers, and decision-makers in obtaining accurate information about the current state and trends of environmental changes. Among these methods, unsupervised classification techniques are widely used due to their independence from labeled training data and their suitability for analyzing large and complex datasets. Objective: The main objective of this research is to design and implement a fast, organized, and accurate unsupervised classification method for Landsat 8 satellite imagery that can be executed in the shortest possible time. The proposed method is based on various spectral indices and combines the K-means algorithm with a simple artificial neural network (ANN), designed in such a way that it does not require any training data. Methodology: In this study, the Landsat 8 satellite image containing 10 main bands (7 multispectral, 2 thermal, and 1 panchromatic) was preprocessed. Several indices were then extracted, including the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), Soil Adjusted Vegetation Index (SAVI), and Dry Bare Soil Index (DBI). Additional features such as brightness, texture, and edge information were also extracted to improveclassseparability.After data normalization, the K-means algorithm was applied for initial clustering, and the results were used as weak labels for the neural network. The designed neural network contained a single hidden layer and received the extracted features as input to refine the clusters and produce the final classification map. The thermal bands were used to distinguish warm and dry soil areas from shaded and cooler regions, while the panchromatic band was utilized to accurately detect urban and suburban road networks. Results: The final classification results demonstrated that the proposed method achieved an overall accuracy of 80.36%, which is considered acceptable. The algorithm successfully distinguished rooftops, barren mountains, bare soils, unpaved areas, and both urban and interurban roads with clear boundaries. The amount of noise in the final unsupervised classification output was significantly reduced, and the spatial consistency of the classes was preserved. Qualitative evaluation in the Sabzevar region showed that the improved unsupervised classification method could accurately identify vegetation, built-up areas, and barren lands with high spatial detail. Furthermore, it effectively separated urban streets from interurban roads. Conclusion: In this research, by utilizing spectral indices such as NDVI, NDBI, NDWI, thermal bands, and an artificial band, along with a simple artificial neural network, an efficient unsupervised classification algorithm was developed. The main goal was to achieve accurate land cover separation in urban and mountainous areas. Despite not using any training data or pre-existing algorithms, the improved unsupervised classification method successfully delineated similar classes such as urban streets, interurban roads, barren mountains, and rooftops with high accuracy. Although the overall accuracy (80.36%) and Kappa coefficient (0.72) were slightly lower than those of traditional algorithms such as SVM and Decision Tree, the spatial quality and class separability of the proposed method were considerably superior. The output maps produced by the improved algorithm are more realistic both visually and analytically. https://gisj.sbu.ac.ir/article_106555.html Introduction: Soil salinity significantly contributes to the degradation of natural ecosystems in arid and semi-arid regions. Timely and effective monitoring and mapping of soil salinity are essential to prevent land degradation and promote sustainable soil management. Remote sensing data is recognized as an effective and accurate tool for identifying soil salinity. Khuzestan Province, one of Iran's agriculturally significant areas, is facing salinity challenges. Therefore, the objective of this research is to map and monitor soil salinity in Bavi County, located in Khuzestan Province, using feature space models based on remote sensing.Materials and Methods: First, the locations of 350 sample points were determined using the conditioned Latin Hypercube Sampling (cLHS) method, and the electrical conductivity (EC) of the soil was measured at depths of 0–10, 10–20, and 20–30 cm. In this study, Landsat-9 data were used to extract optical indices and Sentinel-1 data were used to extract radar indices. After initial corrections were applied to the satellite images, the indices were calculated and normalized using raster calculation tool in ArcGIS 10.8.2 software. In the next step, the Digital Number (DN) values of the corresponding pixels were extracted from each index and the linear regression relationship between the indices was obtained. Accordingly, 12 two-dimensional feature space models consisting of optical and radar indices were constructed in SAGAGIS 9.5 software. The linear classification model of salinization of Hong et al. (2022) was used to prepare soil salinity maps. Finally, the salinity maps were separated into five soil salinity classes based on the classification of Brown et al. (1954) and the Support Vector Machine (SVM) algorithm in ENVI 5.6 software and were validated using the Overall Accuracy, Kappa Coefficient, and Bias parameters.Results and Discussions: Descriptive statistics for the field data indicated a decrease in both the mean salinity and its variability with increasing soil depth. Analysis of the regression relationships between remote sensing indices within the feature space models revealed high coefficients of determination (R²), ranging from 0.814 to 0.973 for optical models and from 0.790 to 0.794 for radar models. Additionally, remote sensing indices in optical feature space models exhibited a stronger correlation compared to those in radar feature space models. After creating the density scatter plots and determining the equation of the best-fit line for each feature space model, the slope of the line perpendicular to the fitted straight line (K) was calculated. After creating the density scatter plots and determining the equation of the best-fit line for each feature space model, the slope of the line perpendicular to the fitted straight line (K) was calculated. Subsequently, linear equations for to determine soil salinity levels in feature space models were derived. Based on these equations, soil salinity maps for each model were generated using ArcGIS 10.8.2. The soil salinity maps obtained from the optical and radar feature space models were then classified into five categories: Non-Saline soils (0-2 dS/m), Slightly Saline soils (2-4 dS/m), Saline soils (4-8 dS/m), Strongly Saline soils (8-16 dS/m), and Extremely Saline soils (>16 dS/m). The classification results of the soil salinity maps using the Support Vector Machine algorithm demonstrated that the optical SI-Albedo feature space model performed best at the 0–10 cm depth, while the radar NRPB-RVI and RVI-NDPI feature space models performed best at the 10–20 cm and 20–30 cm depths, respectively, for estimating soil salinity. The estimations made by these models showed some level of overestimation for EC values through the study area. Conclusions: The salinity classes in the maps generated from the SI-Albedo, NRPB-RVI, and RVI-NDPI models indicated that extremely saline soils, with EC greater than 16 dS/m, were the most frequent and predominantly located in the western parts of the study area. This study demonstrated that using optical and radar feature space models are an effective approach for monitoring soil salinity in arid and semi-arid regions. The maps of soil salinity levels can be utilized to optimize irrigation patterns, develop drainage systems, cultivate salt-tolerant plants, rehabilitate vegetation cover, and plan land use in the affected areas. https://gisj.sbu.ac.ir/article_106570.html Introduction: One of the major health problems in the north of Iran is the production of leachate in landfills and its penetration into water resources, soil, and river sediment. Due to factors such as relatively high rainfall, population density, and elevated groundwater levels in the northern regions of Iran, Mazandaran Province, it is essential to study and scientifically assess landfills and their impact on surface water quality in the rivers. Therefore, in this study, to investigate and prevent water pollution in the Haraz Dam reservoir and preserve water resources and public health, the effect of leachate from landfills at the Emarat site in Amol County is examined on the quality of water resources. The innovation of this study lies in its focus on the use of remote sensing data and the analysis of water quality parameters in the dam reservoir.Materials and Methods: The study area includes Amol city and the Haraz River basin. Amol city, with a population of 400,000, produces about 280 tons of waste daily. This waste is mainly transported to the Emarat site, which is about 45 years old and is located 25 km from Amol, near the Haraz River and Dam. Using Sentinel-2 satellite images and remote sensing analysis in the Google Earth Engine platform, eight water quality parameters that can be measured and calculated using empirical algorithms, including turbidity, suspended particles, pigments, salinity, pH, NH4+-N, CWQI, and depth of points were investigated in the period '2022-11-01', '2022-12-01' for the wet season (December) and the period '2022-06-01', '2022-07-01' for the dry season (July) at three locations (base point, landfill, and dam water). Pearson regression and multiple linear regression models were used to analyze the data.Results and Discussion: The results showed that all the quality parameters studied in Haraz Dam and the Emarat landfill have a significant correlation. The highest correlation was related to salinity (81%), turbidity (79%), and pH (78%). In most cases, the concentration of pollutants or water quality parameters increased from the sample location before the landfill to the landfill, and the intensity of this increase increased towards Haraz Dam. The study of pollutants in the wet and dry seasons also showed that the concentration of pollutants was higher in the dry season than in the wet season, which is due to the decrease in rainfall and the warm weather in this season. Also, the quality parameters of the dam water have changed significantly compared to the base point, indicating the direct effect of leachate on the quality of the dam's reservoir water. The correlations obtained from the Pearson regression model between the dam and landfill points for the water turbidity, suspended particles in water, pH, NH4+-N, water pigment, salinity, bathymetry, and CWQI models were 79%, 43%, 45%, 78%, 78%, 81%, 78%, and 71%, respectively. In contrast, the base point water quality and its impact on the dam water had the highest correlation and were significantly related, indicating a direct impact of the leachate from the building's waste on the water quality of the Haraz Dam and increased water pollution.Conclusion: The results have shown that in most of the quality parameters, there is a significant relationship between Haraz Dam and the Emarat landfill, and in most cases, the concentration of pollutants in the dry season was higher than in the wet season due to the hot weather and other environmental factors. Therefore, the development of waste management systems to reduce pollution and effective management approaches can be a solution to increasing the quality of water resources and public health. The findings of this study will be used by organizations and institutions related to the environment, water resources, and public health. https://gisj.sbu.ac.ir/article_106571.html Background and Purpose: Remote Sensing Technology plays an influential role in environmental protection—and consequently in sustainable development—by enabling the monitoring of natural landscape.The development of technology and its implementation at the regime layer require collaboration between the environmental sector, upstream imagery producer sector and other technology users in adjacent sectors—such as agriculture.Such collaboration entails the providing complementary data (including Ground Level Measurements), establishing processing platforms and data-exchange infrastructures, formulating security and legal regulations, and facilitating the exchange of imagery. The field of Transition Studies is one of the theoretical approaches employed to understand the Contributing factors, challenges, and dynamics of such transformations and interactions. Most studies conducted to date have examined the development and deployment of a technology within a single sector. In practice, however, especially during the diffusion phase of technology, complex and multidimensional interactions take place among organizations both within and across sectors. Comprehending the complexities of multi-sectoral sustainability transitions, together with identifying the influential factors, associated challenges, and suitable policy instruments for accelerating such transitions, represents an active area of research and defines the objectives of the present study.Methods: This research adopts a qualitative methodology and utilize an abductive approach, or inference to the best explanation, to explore the influencing factors, challenges, and policy solutions. Accordingly, a case study strategy focusing on remote sensing technology in environmental protection has been selected. The conceptual framework of the research is grounded in the Multi-Level Perspective (MLP) framework and is complemented by two well-established models to enhance the explanatory power of interactions within the technology value chain, as well as interactions with upstream and adjacent sectors.The primary method of data collection is based on in-depth interviews with twelve key actors involved in remote sensing technology, which are supplemented by selected strategic documents from the upstream communications sector. In line with the research approach, the interviews were in-depth and unstructured. The interview data were analyzed using thematic analysis with the assistance of MAXQDA software.Findings and Discussion: The identified challenges have been categorized into seven groups: technological, policy and regulations, changes in the overall system architecture, increasing interactions between systems, supply factors, demand factors, cultural-psychological and infrastructure factors. The proposed policy instruments are also categorized into four groups: related to supply side of innovation, demand side of innovation, formation of systematic relations, and infrastructure and regulation. The most frequently encountered challenges were related to data and image, which can be categorized into three groups: procurement, development of processing and exchange infrastructure, and data governance. The simultaneous occurrence of challenges in data governance, the absence of a responsible technology owner, and the weak role of intermediary actors has created significant obstacles to inter-sectoral and inter-organizational collaboration.Conclusion: The conceptual framework of the research has enhanced the ability to identify factors and interpret interactions with other sectors. The most significant of these factors are, in relation to the landscape level, the role of international organizations in technology development alongside the intensification of data governance challenges; in relation to the upstream segment of the technology value chain, the development of SAR, satellite constellation and low-cost launch technologies; and, in relation to adjacent sectors, advancements in GIS technology. The design of policies to accelerate this transition should consider the differing logic of government intervention in the environmental sector compared to adjacent sectors, and policy dynamics should correspond to the gradual increase of forces arising from the dual imperatives of participatory governance and sensors synergy. Moreover, if a state-owned enterprise policy instrument is implemented using a combination of data-governance-enhancing tools and intermediary-actor-empowering tools—such as networking and training of interdisciplinary specialists—better outcomes in inter-system collaboration can be achieved. https://gisj.sbu.ac.ir/article_106691.html Modern cities, characterized by rapid population growth and increasingly complex social, economic, and environmental dynamics, face significant challenges in urban management and planning. Factors such as rising population density, unsustainable urban development, pressure on critical infrastructure, environmental changes, and unequal distribution of essential services have rendered traditional urban management approaches insufficient. These challenges highlight the urgent need for innovative, intelligent, and data-driven tools that can enhance urban governance, improve service delivery, and enable sustainable development. Among emerging technologies, digital twins have gained significant attention as a promising solution. Digital twins, defined as three-dimensional, dynamic, and interactive virtual replicas of real-world urban environments, provide the capability to predict urban performance in real time, thus bridging the gap between planning, policy-making, and implementation.Digital twin technology integrates real-time data, advanced modeling techniques, artificial intelligence (AI), and the Internet of Things (IoT) to create a comprehensive, continuously updated representation of urban systems. By doing so, it enables precise, optimized, and data-driven decision-making in urban management. Furthermore, it provides valuable insights into the interactions between urban components, spatial relationships, and the potential impacts of policy interventions, facilitating more informed and proactive governance. In addition to supporting operational and strategic decision-making, digital twins enhance urban design processes, promote social participation, increase transparency in governance, and improve overall urban productivity .The present study focuses on the development and implementation of a digital twin model for District 3 of Tehran Municipality. A comprehensive dataset was collected, including spatial and descriptive information such as GIS maps, land-use layers, street networks, population demographics, building heights, and land-use data. These datasets were further complemented and validated through extensive field surveys to ensure accuracy and reliability. The collected data were first modeled in CityEngine using procedural rules (CGA), allowing for the creation of detailed three-dimensional representations of urban structures. Subsequently, the model was integrated into the ArcGIS environment to enable advanced spatial analyses, spatiotemporal scenario simulations, service accessibility assessments, and evaluations of the potential impacts of urban policies. The resulting digital twin model encompassed residential and commercial buildings, urban facilities, healthcare centers, parks, green spaces, and transportation networks, featuring detailed 3D visualization, real-time update capabilities, and dynamic interaction functionalities.The results of this study demonstrate that digital twins have diverse and multifaceted applications in urban management. They facilitate advanced urban design and scenario simulations prior to real-world implementation, allowing policymakers and planners to evaluate potential outcomes, risks, and trade-offs. Digital twins also enhance citizen engagement by providing accessible visualizations and interactive platforms for public participation, fostering greater transparency and accountability in governance processes. Additionally, these models serve as long-term repositories of urban data, supporting evidence-based decision-making and enabling longitudinal analyses. Beyond administrative and planning benefits, digital twins offer economic and commercial opportunities, such as virtual tourism, immersive city experiences, and location provisioning for film, animation, and entertainment industries. By providing a live, dynamic, and interactive version of the city, the model simulates interactions among urban components, spatial relationships, and mutual influences, transforming urban decision-making from an experiential and estimation-based process into a predictive, data-driven approach.But, several challenges and limitations were identified. These include incomplete access to high-quality data, the need for substantial temporal and financial investment, technical challenges related to modeling and data integration, and the requirement for organizational cultural change to fully leverage digital technologies. Nevertheless, the integration of CityEngine and ArcGIS demonstrated the feasibility of developing a practical and operational digital twin, capable of informing urban policy-making, planning, and management decisions.In conclusion, this study highlights that digital twins, as multidimensional and dynamic urban tools, provide significant potential for scenario simulation, data analysis, social engagement, improvement of service quality, and enhanced transparency in urban management processes. The adoption of digital twin technology offers a practical and scientifically grounded framework for sustainable planning and development in major Iranian cities. Furthermore, it functions as a virtual urban laboratory for city managers, designers, and researchers, enabling experimentation, evaluation, and optimization of urban policies and designs in a controlled, risk-free environment. By presenting an operational model for District 3 of Tehran, this research provides a practical and generalizable example for other urban regions in Iran, demonstrating the transformative potential of digital twins for creating smarter, and more participatory cities. https://gisj.sbu.ac.ir/article_106699.html Introduction: Flight delays are one of the major problems in the aviation industry. Previous studies have looked less at the reserve aircraft and the effect of their deployment location in reducing delays. These few studies show that most airlines deploy these aircraft at their hubs. As such, in this research was used agent-based simulation in combination with the Bees Meta-Heuristic Algorithm for site selection of these aircraft. The agent-based simulation allows the placement of reserve aircraft at different airports and the calculation of the average delay in flights. The bees algorithm also allows the finding of the optimal position of the reserve aircraft to reduce flight delays in a short time. On the other hand, this algorithm was combined with the ant colony optimization meta-heuristic algorithm. The review of results of this combination in improving the performance of the bees algorithm is one of the main goals of the research. Another purpose is to investigate the effect of proper site selection of reserve aircraft in reducing delays compared to their deployment in hubs.Materials and methods: In this study, Anylogic software and its GIS map were used. Also, the flight data of Qeshm Air airline was used as real data. The simulation was done as agent-based, including the main agent, the airport agent, the main aircraft agent, and the reserve aircraft agent. At the beginning of the simulation, the main aircraft will fly to their destination based on time of their flights per week and then return to the origin. In the following, airports will call their nearest reserve aircraft in the event of an aircraft failure. The reserve plane will immediately move to the destination of the cancelled flight after arriving at the requesting airport. It will then return to its origin airport. The average flight time of all reserve aircraft to the requesting airports in the total simulation time was considered as the average delay in flights. This average delay is used as the objective function required for each bee in the execution of the bees algorithm. On the other hand, the bees meta-heuristic algorithm was combined with the ant colony optimization algorithm in 3 proposed scenarios. The first, second, and third scenarios were considered as combination in the local search section of the algorithm, combination in the global search section, and simultaneous combination in both sections, respectively. Then, with 50 independent runs of each of the combined algorithms and the initial algorithm with 15 replications each, the effect of these scenarios on improving the performance of the bees algorithm was investigated.Results and Discussion: The results showed the significant effect of all three scenarios in improving the performance of the bees algorithm in three parts of the algorithm convergence, the repeatability of the results, as well as the average number of repetitions to achieve the optimal solution (the best result found). The third scenario, as the most effective scenario, in the repeatability of the results section, led to 50 optimal solutions out of 50 implementations compared to 3 optimal solutions in the initial bees algorithm, which is a very impressive result. Also, this scenario, the average number of replications in the initial bees algorithm to achieve the best result, which was 14.56, with a 57% reduction, changed to 6.26 replications. The first and second scenarios were ranked next in order of effectiveness, respectively. Also, the proposed hybrid algorithm showed appropriate and acceptable performance compared to similar hybrid algorithms in other research. On the other hand, the results of the research showed the significant effect of about 60% of the appropriate site selection of reserve planes in reducing flight delays compared to deploy them in hubs. Also, the results showed an effect about 87% in reducing delays compared to the worst deployment of reserve aircraft, as the greatest effect of their suitable site selection.Conclusion: The results show that proper site selection of reserve aircraft can significantly reduce flight delays. On the other hand, meta-heuristic algorithms showed their appropriate efficiency in the site selection of reserve aircraft. Also, the results of the research showed that creative combinations of meta-heuristic algorithms, such as the proposed combination in this study, can have a significant effect on improving their performance. https://gisj.sbu.ac.ir/article_106718.html Introduction: Digital Elevation Models, also known as DEM, are widely utilized tools in Earth sciences, particularly in geomorphological studies. Although various DEMs with distinct characteristics exist, only a limited number are freely accessible to researchers. Furthermore, not all DEMs exhibit identical performance. Factors such as pixel or cell size and the algorithm employed in DEM generation are among the most critical elements influencing their performance. Therefore, one of the most crucial considerations in employing DEMs is selecting the most suitable and optimal model for geomorphological studies. In this context, the present study aims to identify the most appropriate DEM by evaluating four commonly used and freely available models. Ultimately, based on the performance of each model, the most suitable DEM for geomorphological investigations will be determined. Selecting an appropriate DEM will contribute to producing high-quality studies and obtaining reliable results in geomorphological research.Materials and Methods: This study utilized four freely available DEMs including SRTM, ASTER, AW3D30, and ALOS PALSAR. The spatial resolution of the first three models is approximately 30 meters, while that of ALOS PALSAR is 12.5 meters. To quantitatively assess the performance of these DEMs, the study employed parameters such as the Root Mean Square Error, geomorphons, slope, hypsometric curve, and cross-sectional profile. By selecting these parameters, the DEMs were evaluated from various aspects, including vertical accuracy, horizontal accuracy, and the impact of cell size. Additionally, to mitigate errors inherent in the DEMs, the Fill operation was applied to all models used in the study. The fill sink tool is available in most of the commonly used GIS software.Results and Discussion: According to the RMSE index, the AW3D30 model exhibited the lowest error with a value of 6.77, followed by the SRTM and ALOS PALSAR models with values of 7.36 and 8.02, respectively, while the ASTER model showed the highest error with a value of 11.95. The comparison of geomorphon classes revealed that the ALOS PALSAR model produced a total class area of 120.76 km², which is the closest estimation to the actual area of the region (121.5 km²). In contrast, the other three models yielded similar areas of approximately 119.9 km². The results further indicated that the SRTM model provided landform classifications, including valleys with an area of 10.6 km², that were closest to those derived from the ALOS PALSAR model (8.96 km²). The analysis of slope values also demonstrated that the ALOS PALSAR model recorded the steepest maximum slope, equivalent to 74.73°, whereas the maximum slope values in the SRTM, AW3D30, and ASTER models were 68.99°, 68.37°, and 66.36°, respectively. The hypsometric curves likewise showed that the ALOS PALSAR and SRTM models exhibited similar performance; for example, at a relative elevation of 39, the corresponding relative areas were 94.80 and 95.94, while the corresponding values for the ASTER and AW3D30 models were 88.84 and 89.47, respectively. The cross-sectional profiles indicated that the ASTER model had the lowest vertical accuracy and tended to overestimate elevation values compared to the other models.Conclusion: In this study, a set of tools was employed to assess and identify the most suitable DEM for geomorphological studies. Based on the findings, despite the superior spatial resolution of the ALOS PALSAR model, the SRTM model emerged as the most appropriate freely available DEM for geomorphological applications, particularly in Iran. The primary reasons for selecting this model include its nationwide spatial coverage and its performance, which closely approximates that of the ALOS PALSAR model. Additionally, one of the key limitations identified in this study was the absence of high-precision local models for result validation. Consequently, for future studies, it is recommended to utilize a high-resolution DEM to enhance the accuracy and reliability of validation processes. https://gisj.sbu.ac.ir/article_106744.html Background and Objective: Snow cover is one of the most influential surface components, playing a key role in regulating energy exchange, controlling land surface temperature, and governing climatic dynamics in mountainous regions. In recent decades, particularly at mid-latitudes and high elevations, rising temperatures have altered snow accumulation and melt patterns, with significant consequences for water resources, natural hazards, and local climate. The high-altitude areas of Mazandaran Province, located on the slopes of the Central Alborz Mountains, are especially vulnerable due to steep thermal gradients, altitudinal variability, and high dependence on winter snowfall. Despite its importance, a quantitative, multi-metric, and spatiotemporal analysis of the relationship between LST and snow depth in this region has been limited. The main objective of this study is to quantify the intensity, direction, and nature of the relationship between LST and snow depth and to identify dominant thermal–snow regimes in the highlands of Mazandaran Province.Materials and Methods: Snow depth data from the GLDAS model and LST data derived from the MODIS sensor for the period 2018–2024 were used in this study. Analyses were conducted for five high-altitude stations—Alasht, Baladeh, Kiasar, Kojur, and Siah-Bisheh—representing diverse elevation conditions in the Central Alborz region. To examine the dependency between variables, complementary statistical indices including Pearson and Spearman correlations, MI, and R² were employed. Additionally, K-means clustering was applied to identify common behavioral patterns and thermal thresholds. To investigate spatiotemporal variations, annual LST and snow depth maps were produced and analyzed for the entire Central Alborz region of Mazandaran.Results and Discussion: Statistical analyses consistently revealed a strong, significant, and negative relationship between LST and snow depth across all stations. Pearson correlation coefficients ranged from -0.58 to -0.77, and Spearman coefficients ranged from -0.76 to -0.91, indicating a stable inverse dependency between rising temperatures and decreasing snow depth. The notable differences between Pearson and Spearman coefficients suggest that the relationship is not purely linear, with nonlinear components playing a significant role. This finding was further supported by MI values ranging from 0.3 to 0.61, highlighting the influence of complex feedback mechanisms such as albedo effects, latent heat of melt storage, and variations in surface heat fluxes on the snow–temperature interaction. The strongest relationship was observed at the Siah-Bisheh station, where Pearson and Spearman coefficients reached -0.77 and -0.91, respectively, with an R² value of approximately 60%. This emphasizes the high sensitivity of the snow–temperature system at higher elevations and the key role of snow in moderating land surface temperature. K-means clustering identified three distinct thermal–snow regimes across all stations: warm snow-free conditions, transitional periods with unstable snow, and cold conditions with stable snow accumulation. These clusters clearly delineated temperature thresholds governing snow accumulation and melt, indicating that at temperatures near or below 0°C, snow significantly reduces LST through increased albedo and decreased surface energy absorption. Spatiotemporal analysis of annual maps revealed pronounced interannual variations. In 2019, with maximum snow depths reaching approximately 1.2 meters, the lowest LST values were recorded over extensive high-elevation areas. Conversely, in 2021 and 2022, reduced snow depths (maximum ~0.08 meters) coincided with LST increases exceeding 2°C. These patterns directly confirm the negative snow–temperature feedback and the high vulnerability of mountainous systems to reductions in snow cover.Conclusion: The findings indicate that reductions in snow depth and coverage in the highlands of Mazandaran Province have a direct impact on increasing land surface temperature, potentially intensifying melt processes, altering runoff timing, and reducing water resource stability. The high sensitivity of the snow–temperature relationship in high-altitude stations underscores the importance of precise monitoring and modeling of these systems under warming climate conditions. Accordingly, the application of regional climate models based on global warming scenarios, along with the expansion of ground-based monitoring networks in high-altitude areas, is recommended as a key strategy for water resource management and mitigating climate change impacts in the region. https://gisj.sbu.ac.ir/article_106802.html Introduction: Arid and semi-arid regions are highly vulnerable to both climatic variability and human activities, making continuous and accurate monitoring of reservoir water levels an indispensable task. This study aimed to quantitatively separate and evaluate the relative contributions of climatic and anthropogenic factors to water-level changes at Kajaki Dam, Afghanistan, and to assess the downstream impacts on the Helmand River in southern Iran over the past decade (2013–2023). Kajaki Dam, with a storage capacity of 1.4 billion cubic meters, plays a crucial role in meeting water demands and sustaining the Helmand River ecosystem. Methods: This research employed multi-sensor satellite imagery, including 45 Landsat-8 OLI/TIRS and 62 Sentinel-2 MSI images. Images were temporally synchronized within a ±15-day window, and only images with less than 10% cloud cover were selected. Preprocessing steps, including atmospheric correction and cloud removal, were performed using SREM and Sen2Cor algorithms. Eleven spectral indices were computed using customized equations and cloud-based processing on the Google Earth Engine (GEE) platform to enable high-precision analysis. Water extent was extracted using Otsu thresholding and decision tree classification with 300 training samples. Evaluation metrics included RMSE, R², Nash–Sutcliffe efficiency (NS), MAE, and K-Fold cross-validation. Climatic data were sourced from ERA5, and in situ measurements were collected at 50 ground control points, including water–land boundaries and shallow and deep water areas, using GPS with ±3 m accuracy. Time-series analyses were employed to assess long-term trends in water surface dynamics and to quantitatively separate the impacts of climatic factors (precipitation, temperature, and actual evapotranspiration) and human activities (agricultural expansion, new dam constructions, and reservoir operation) on water level changes. Results an con colousion: Spectral index analysis revealed that the S2WI index provided the highest accuracy in monitoring water extent, with R² = 0.96, RMSE = 1.46 km², and NS = 0.96. This index effectively distinguished water from other land cover types while reducing errors caused by vegetation and soil. Comparative analysis of Landsat-8 and Sentinel-2 sensors indicated that both were capable of monitoring water surface changes; however, Sentinel-2 outperformed Landsat-8 due to its higher spatial resolution and shorter revisit interval, particularly for capturing short-term dynamics. Multi-temporal comparative studies confirmed that indices such as S2WI and MNDWI can accurately track changes in water extent. The water surface area of Kajaki Dam declined from 32.48 km² in 2014 to 22.18 km² in 2021, representing a 31.7% total reduction and an average annual decrease of approximately 4.5%. Multivariate regression analysis indicated that the combined effects of climatic and anthropogenic factors drove reductions in water extent and inflow. Approximately 60% of the decrease was attributed to climatic variables, including an annual precipitation averaging 196.8 mm with high interannual variability (CV = 42%) and a statistically non-significant upward trend of 3.3 mm/year; mean land surface temperature of 22.63°C with notable fluctuations and a slight decreasing trend; and actual evapotranspiration averaging 1,432 mm/year, strongly correlated with precipitation (r > 0.85), indicating a water-limited regime. The remaining 40% was associated with human activities, including the expansion of irrigated agriculture, the construction of multiple upstream control structures, and alterations in reservoir operation, demonstrating that water inflow reductions cannot be attributed solely to climatic changes. This ongoing decline is causing severe economic, environmental (destruction of the Hamoun Wetland) and social (migration) impacts. The integration of multi-sensor satellite data with cloud-based processing on GEE enabled precise, repeatable monitoring of water dynamics. It provided a quantitative framework for separating the contributions of climatic and anthropogenic drivers. These findings offer a robust basis for future water resource management in the Helmand River basin, supporting adaptive strategies to mitigate the impacts of both environmental variability and human interventions. https://gisj.sbu.ac.ir/article_106803.html Introduction: Due to their valuable and dynamic role, wetlands are often neglected in development policies and plans, which has led to rapid degradation and destruction. The Anzali International Wetland, which was once known as one of the richest and most beautiful wetlands on the southern shore of the Caspian Sea and even in the whole of Eurasia, is now on the verge of becoming a dry and lifeless marsh, as the average water depth has reached from 4.5 meters in the 1350s to less than 70 cm in 1404 and in many central areas of the lagoon, the depth has reached less than 30 cm. The research conducted on Anzali lagoon has paid less attention to a comprehensive evaluation of the root causes of the ecological and socio-economic threats to its destruction. Therefore, this issue underscores the need for a comprehensive study that identifies the root causes of degradation, with a focus on local anthropogenic factors. For this purpose, the aim of this research is to comprehensively identify the root causes of the destruction of the Anzali wetland, evaluate the performance of past management measures, and provide integrated, sustainable local management approaches for the long-term restoration and protection of this vital ecosystem. Materials and methods: In the current research, in order to accurately identify the pressures and environmental threats on Anzali wetland, a combination of methods including a) conducting numerous field visits by the authors, b) collection of specialized information from experts of the General Department of Environmental Protection of Gilan province, and c) review and use of scientific articles, reports and published books related to Anzali wetland. Also, the data was organized in an integrated manner and the pressures and threats were listed for each of the rivers leading to the wetland separately and by type. Then, using aerial images and GPS location data, the threat points in the Anzali lagoon watershed were mapped in ArcGIS. In the following, the multi-criteria decision analysis (MCDA) method was used to prioritize the main threats related to the rivers entering the Anzali lagoon. The MCDA method used in this research was a simple weighted sum model. Results: Based on the findings of this research, 56 main threats were recorded and observed in the rivers leading to Anzali Wetland, and for ease of prioritization, all of them were placed in 8 groups. According to the results, sedimentation and pollution had the highest scores, indicating that these factors can directly change the structure of the wetland. Moderate ratings included threats from invasive species and water abstraction/dam construction. Finally, the lower ranks included climate changes and Caspian regression, which, despite their high intensity, were ranked lower due to their low local (mainly global) controllability. Discussion and Conclusion: This study provided a comprehensive picture of the environmental pressures on this valuable ecosystem using a mixed-methods approach. By identifying the pressures and threats on the Anzali wetland, he highlighted the need for a local approach to preserve it. The native model proposed in this research, inspired by successful global experiences and adapting them to the native conditions of Iran and the special characteristics of the Anzali wetland, is based on two main foundations, including: 1) Ecosystem-based management, which, unlike traditional management that often focuses on one factor, considers all degradation factors simultaneously and with a systemic view and 2) multi-level governance by establishing a single coordination council of Anzali wetland at the provincial level (with the presence of representatives of all relevant institutions, non-governmental organizations, local communities and experts) and its connection with the national and international (Ramsar Convention Secretariat) responsibilities will be clear and synergistic, in order to prevent the failure of scattered projects. This proposed indigenous model is fully consistent with the international frameworks of the Ramsar Convention and the Convention on Biological Diversity, as it emphasises the wise use of wetlands, the preservation of biodiversity, and the participation of local communities. The successful implementation of this model can be used as a local model for the management of other wetlands in Iran. https://gisj.sbu.ac.ir/article_106804.html Introduction: Despite the emerging developed methods in photogrammetric engineering, aerial photogrammetry based on its traditional instructions is still known as a conventional method for generating spatial information over large regions. Aerial triangulation is a crucial step in preparing aerial images for extracting spatial information. Bundle adjustment is the most common method of performing aerial triangulation, in which exterior orientation parameters of images are estimated through Ground Control Points (GCPs), tie points, and other auxiliary observations. In photogrammetric engineering, by reducing the necessity for ground control points in the aerial triangulation process, strategic goals such as achieving direct georeferencing and reducing operational costs have been pursued. Integrating various spatial data sources to facilitate the aerial triangulation process is known as a traditional approach in photogrammetric engineering. So far, the contribution of navigation data, maps, geometrical constraints of manmade and natural features, and ortho-images alongside GCPs has been used for this purpose. In this research, the idea of using High Resolution Satellite Images (HRSI) along with their refined Rational Polynomial Coefficients (RPCs) to participate in aerial triangulation has been proposed. This was done using tie points measured between HRSI and aerial images. The uniformity in georeferencing accuracy of HRSIs has been the motivation for using such data sources to prevent systematic deviations in aerial triangulation within the spatial resolution of satellite images. Materials and Methods: The proposed method introduces tie points between aerial and satellite images as new observations in the bundle adjustment. The rational functions associated with the HRSI produce the condition equations for these tie points. Before using the initial RPCs published along with HRSI, their preparation process, including geometric refinement and changing their ground coordinate systems, is performed. In the bundle adjustment process, the coefficients of the refined rational functions are held constant; their role is limited to helping in estimating the exterior orientation parameters of the aerial images and the 3D coordinates of tie points. The precision difference arising from the spatial resolution disparity between aerial and satellite imagery is addressed by tuning the stochastic model using variance component estimation. The method was evaluated using a block of aerial images captured by an UltraCamD camera and a WorldView II satellite image, both of which covered a part of Tehran city. The indirectly refined RPCs of WorldView II were utilized, and the required tie points between the aerial and satellite images were measured manually by an expert. Results and Discussion: The results of this research were evaluated in three different scenarios. The results demonstrated the success of the proposed method in reducing the necessity for GCPs in aerial triangulation and preventing to face of its problems of deficiencies in the definition of the ground coordinate system. Using this method, even with a single GCP, has achieved competitive accuracies compared to using multiple control points in bundle adjustment. However, if there is an appropriate number of control points in the bundle adjustment, this solution will not have a noticeable effect on the aerial triangulation results. Conclusion: Integrating HRSIs and their refined RPCs, as described, effectively reduces the dependency on GCPs in the aerial triangulation process. Future research should investigate the effect of the spatial resolution ratio of satellite and aerial images on the results, as well as the potential of using stereo satellite images to enhance the capabilities of this method further. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . https://gisj.sbu.ac.ir/article_106805.html Introduction: Urban traffic safety is a critical challenge in metropolitan areas, where accidents are influenced by factors like travel demand, vehicle ownership, and road networks. Traditional regression models often assume spatial stationarity, limiting their ability to capture spatial and temporal heterogeneity in accident patterns. To address this, this study applies a Geographically and Temporally Weighted Regression (GTWR) model to analyze and predict accident rates across Traffic Analysis Zones (TAZs) in Mashhad, Iran. The primary aim is to evaluate the local spatio-temporal effects of key variables and compare GTWR’s performance against a global regression model. Materials and Methods: For this study, four years of traffic accident data (2021–2024) were collected and standardized for 253 TAZs in Mashhad. This was combined with independent variables related to travel demand (vehicle kilometers traveled and the number of generated trips), vehicle ownership, and infrastructure (number of unsignalized intersections). A global regression model was estimated first, followed by the calibration of the GTWR model. Model development used data from the first three years (2021–2023), with 70% randomly selected for training and calibration. The coefficient of determination (R²) and Residual Sum of Squares (RSS) were used to evaluate calibration. The remaining 30% of the data from these years were used for testing and validation, with model accuracy assessed using the correlation coefficient (R²). To evaluate predictive performance, data from 2024 was employed, and results were examined using the Pearson correlation coefficient (R²) and Mean Squared Error (MSE). Additionally, the bivariate Moran’s I index was applied to examine spatio-temporal autocorrelation in the original data and the model residuals. Results and Discussion: Preliminary data analysis indicated that the traffic accident rate exhibited significant positive spatio-temporal autocorrelation, highlighting the necessity of using local models like GTWR. The findings demonstrate that the GTWR model significantly outperformed the global regression model. Specifically, the R² increased from 0.38 in the global model to 0.87 in the local model, while the RSS values showed a substantial reduction (62935.6 vs. 654567.76). Validation using the testing dataset confirmed this, with an R² of 0.83 for GTWR compared to 0.71 for the global model. Furthermore, predictions for 2024 revealed that GTWR achieved superior predictive performance, evidenced by a lower MSE (1.28 vs. 8.4) and a higher correlation coefficient (0.84 vs. 0.64) relative to the global model. The spatially varying local coefficients indicated pronounced spatio-temporal non-stationarity. For instance, the effect of vehicle kilometers traveled (VKT) was stronger in central and northern parts of the city, while weaker effects were observed in the southern zones. The automobile ownership (ACO) variable exhibited a positive and stable association with accident rates, particularly in central and high-density areas. Conversely, the number of unsignalized intersections showed stronger effects in the western and northwestern parts. The number of generated trips had a positive impact across all zones but exhibited greater spatio-temporal stability compared to the other variables. The bivariate Moran’s I results indicated that the residuals of the global model still suffered from spatio-temporal autocorrelation, whereas this issue was effectively mitigated in the GTWR model. Conclusion: The results demonstrate that in urban traffic accident analysis, using local spatio-temporal models like GTWR can provide a more accurate representation of influencing factors by capturing spatial and temporal heterogeneity. Compared to global models, GTWR not only achieved a better fit but also revealed localized patterns in the effects of explanatory variables. These findings confirm the importance of travel demand and roadway infrastructure in urban traffic accidents and can serve as a foundation for targeted safety policies. Based on the results, focusing on urban travel demand management, controlling private car ownership and usage in high-density areas, and improving the safety of unsignalized intersections, particularly in the western and northwestern parts of the city, can help reduce accident rates. Ultimately, this study shows that, in addition to higher predictive accuracy, the GTWR model is an effective tool for prioritizing high-risk areas and optimizing the allocation of safety resources in urban planning. https://gisj.sbu.ac.ir/article_106891.html The accurate and timely prediction of urban traffic states constitutes a cornerstone of effective route optimization, travel time minimization, and the advancement of intelligent transportation systems (ITS). In megacities, where traffic dynamics exhibit heightened complexity due to intricate spatial interactions and rapidly evolving temporal patterns, there is an imperative for models that jointly capture spatiotemporal dependencies with high fidelity. Conventional fixed sensing infrastructures—such as inductive loop detectors and surveillance cameras—while widely deployed, suffer from substantial installation and maintenance costs, restricted spatial coverage, and reliance on static infrastructure, thereby limiting their scalability and practicality in large-scale urban environments. This study introduces a novel data-driven spatiotemporal framework tailored for short-term traffic state estimation and forecasting across the extensive highway network of Tehran. The approach harnesses publicly accessible Google Maps traffic imagery as a scalable, low-cost alternative data source, yielding a comprehensive dataset comprising four-level congestion classifications sampled at 15-minute intervals over a three-month period. This large-scale, real-world corpus effectively encapsulates traffic dynamics across diverse congestion regimes throughout the city's highway system. Initial descriptive statistical analyses elucidated pronounced recurrent peak-hour patterns and statistically significant weekday–weekend disparities, establishing a robust empirical foundation for subsequent predictive modeling. In the core modeling stage, we propose a hybrid spatiotemporal architecture that integrates Graph Convolutional Networks (GCN) with Temporal Convolutional Networks (TCN). The highway network is modeled as a graph, with nodes representing individual highway segments and edges reflecting spatial adjacency. Graph convolution operations effectively capture localized spatial dependencies and congestion propagation effects among neighboring segments, while one-dimensional temporal convolutions model non-stationary temporal evolutions and dynamic traffic trends. In contrast to recurrent architectures, the GCN–TCN paradigm supports fully parallelizable computations, yielding superior training efficiency and markedly reduced computational overhead while preserving intricate spatiotemporal correlations. The proposed model's predictive efficacy was rigorously assessed across 15-, 30-, and 60-minute horizons using Accuracy and macro F1-score as primary evaluation metrics. Comparative benchmarking against three competitive baselines—Historical Average, standalone Long Short-Term Memory (LSTM), and TCN without explicit spatial modeling—demonstrated consistent superiority of the GCN–TCN framework across all horizons. For the 15-minute forecast, the model attained an Accuracy of 0.70 and F1-score of 0.66, surpassing the strongest baseline (TCN) at 0.65 and 0.64, respectively. At the 30-minute horizon, performance reached 0.68 Accuracy and 0.63 F1-score, outperforming LSTM (0.63/0.58) and TCN (0.64/0.62). Even at the 60-minute horizon, the model sustained strong results with 0.64 Accuracy and 0.60 F1-score. Relative to the Historical Average benchmark, the proposed framework delivered improvements of up to 15% in Accuracy and 16% in F1-score, with particularly pronounced gains under moderate-to-heavy congestion regimes—underscoring enhanced robustness against class imbalance and sudden traffic perturbations. Collectively, these results affirm that the synergistic integration of cost-effective, image-derived traffic data with graph-informed spatiotemporal deep learning architectures offers a highly efficient, scalable, and economically viable pathway for short-term urban traffic forecasting. The explicit modeling of road network topology emerges as a pivotal factor in elevating predictive precision, laying a solid groundwork for the deployment of real-time traffic systems and advanced decision-support platforms in metropolitan traffic management. Collectively, these results affirm that the synergistic integration of cost-effective, image-derived traffic data with graph-informed spatiotemporal deep learning architectures offers a highly efficient, scalable, and economically viable pathway for short-term urban traffic forecasting. The explicit modeling of road network topology emerges as a pivotal factor in elevating predictive precision, laying a solid groundwork for the deployment of real-time traffic systems and advanced decision-support platforms in metropolitan traffic management. Collectively, these results affirm that the synergistic integration of cost-effective, image-derived traffic data with graph-informed spatiotemporal deep learning architectures offers a highly efficient, scalable, and economically viable pathway for short-term urban traffic forecasting. The explicit modeling of road network topology emerges as a pivotal factor in elevating predictive precision, laying a solid groundwork for the deployment of real-time traffic systems and advanced decision-support platforms in metropolitan traffic management. https://gisj.sbu.ac.ir/article_106892.html Background and aim: Landslides, as a major geomorphological hazard, threaten transportation safety along mountainous roads due to their severe human, economic, and environmental impacts. In this context, spatial landslide susceptibility modeling—considered a key step in landslide hazard and risk assessment—plays a crucial role in mitigating potential damages. In recent years, the rapid development of machine learning algorithms has significantly enhanced the capability of spatial modeling for landslide susceptibility. The main objective of this study is to apply the random forest machine learning algorithm to model the spatial susceptibility of landslide occurrence along the Haraz mountainous road. Haraz road is continuously exposed to various types of landslides due to its complex and diverse geological structures, landslide-prone lithological conditions, climatic factors, and intensive human activities, and is regarded as one of the most hazardous mountainous roads in Iran. Materials and methods: To model landslide susceptibility, the spatial distribution of landslides was first identified and compiled as a landslide inventory map. This inventory was prepared based on detailed field surveys, geological maps, and satellite images. Subsequently, a set of independent conditioning factors including geological, topographic, hydrological, vegetation, land-use and land-cover, and human-related factors, were generated within a one-kilometer buffer zone along the Haraz road. Due to the imbalance between landslide and non-landslide pixels in the study area, a balanced dataset with an equal number of landslide and non-landslide pixels was constructed. From this dataset, 70% of the pixels were randomly selected for model training, while the remaining 30% were used for validation. To evaluate the effect of random data partitioning on model performance, a 10-fold cross-validation approach was implemented within the random forest algorithm, and the training–testing process was repeated ten times. In addition, to improve the predictive performance of the random forest model, hyperparameter tuning was applied. Key algorithm parameters, including the number of decision trees and the number of variables selected at each node of split, were systematically tuned. The accuracy and performance of the ten training models and ten validation models were evaluated using confusion matrix, Kappa coefficient, and the Area Under Curve (AUC). Finally, the model with the highest AUC value in the validation stage was selected as the optimal model and used to generate spatial landslide susceptibility map. Resulst and discussion: The results related to the importance of conditioning factors affecting landslides in random forest algorithm, indicate that the geology is the most influential variable controlling landslide occurrence along the Haraz road, with a relative importance of 47.8%. In this regard, geological units consisting of scree deposits and the Shemshak formation play a dominant role in triggering landslides in the study area. Regarding the spatial modeling of landslide susceptibility using the random forest machine learning algorithm combined with a 10-fold cross-validation approach, the results demonstrate a high predictive accuracy and robust performance in identifying landslide-prone areas. The mean Area Under the Curve (AUC) values obtained from the ten training iterations and ten validation iterations were 0.93 and 0.85, respectively, indicating the strong capability of the proposed approach for reliable landslide susceptibility assessment along mountainous road corridors. Conclusion: The results indicate that landslide spatial susceptibility along the Haraz road is variable and heterogeneous. Within the one-kilometer buffer zone along the road corridor, approximately 130 km² of the study area is classified as high and very high prone landslide areas, encompassing nearly 36 km of the Haraz road length. The findings of this study provide valuable insights for geomorphological hazard management along this road and can be effectively used for prioritizing technical and engineering interventions. In particular, the generated landslide susceptibility map can support the assessment of unstable slopes, the implementation of slope stabilization measures in high- and very high-risk zones, and strategic planning aimed at enhancing road safety and reducing landslide-related risks. https://gisj.sbu.ac.ir/article_106893.html Extended Abstract Background and Objectives Floods are among the most destructive natural hazards, particularly in arid and semi-arid regions, causing extensive damage to urban areas, infrastructure, agricultural lands, and water resources. Climate change, increased extreme rainfall events, unplanned urban development, and land-use changes have intensified the frequency and severity of floods in recent decades. In this context, accurately identifying flood-prone areas and producing susceptibility maps play a crucial role in risk management, land-use planning, and damage mitigation. However, the lack of hydrological and ground-based data in many regions, including the Birjand Plain, limits the effectiveness of conventional hydrological methods. Consequently, leveraging remote sensing data, spectral indices, and machine learning algorithms has emerged as a novel, rapid, and cost-effective approach. The main objective of this study is to develop an integrated framework for flood susceptibility mapping in the Birjand Plain using the Normalized Difference Flood Index (NDFI), Google Earth Engine (GEE), and machine learning algorithms, and to evaluate and compare their performance. Materials and Methods In this study, satellite imagery was first processed in the Google Earth Engine environment. After applying preprocessing steps and cloud removal, the NDFI was computed. Using field surveys and historical aerial photographs from the 1960s, a binary map of flood and non-flood areas was produced. Based on this map, flood occurrence locations were extracted and used for model training and validation. Fifteen geo-environmental factors influencing flood occurrence, including topographic, hydrological, climatic, and land-cover parameters, were extracted and prepared as raster layers with a spatial resolution of 30 × 30 m. To prevent multicollinearity, correlations among factors were examined. Subsequently, four machine learning algorithms—Random Forest (RF), AdaBoost, Gradient Boosting (GB), and a hybrid RF–GB model—were applied to model flood susceptibility. Model performance was evaluated using Accuracy, Sensitivity, Specificity, F1-Score, Kappa coefficient, RMSE, and the Area Under the ROC Curve (AUC). Results and Discussion The results indicated that all machine learning models demonstrated acceptable capability in predicting flood-prone areas; however, differences in accuracy and stability were observed among them. The Random Forest model exhibited the best overall performance, with the highest discriminative ability (AUC = 0.9), overall accuracy (Accuracy = 0.83), and complete sensitivity in identifying flood-prone areas (Sensitivity = 1, Specificity = 0.6, F1 = 0.87, Kappa = 0.64), along with the lowest error (RMSE = 0.39). Gradient Boosting (AUC = 0.78, RMSE = 0.49, Accuracy = 0.75, Sensitivity = 1, Specificity = 0.4, F1 = 0.82, Kappa = 0.49) and AdaBoost (AUC = 0.82, RMSE = 0.43, Accuracy = 0.66, Sensitivity = 0.71, Specificity = 0.6, F1 = 0.71, Kappa = 0.31) also showed reasonable ability to identify flood-prone areas, but ranked lower in terms of balance between sensitivity and specificity. The hybrid RF–GB model, despite a relative improvement in discriminative ability (AUC = 0.88, RMSE = 0.41, Accuracy = 0.75, Sensitivity = 1, Specificity = 0.4, F1 = 0.82, Kappa = 0.43), did not demonstrate a significant advantage over the Random Forest model.Flood-prone maps were classified into five categories: very low, low, moderate, high, and very high. Spatial pattern analysis revealed that areas with high and very high susceptibility were predominantly located in low-elevation zones with gentle slopes, close to rivers, and with sparse vegetation cover, highlighting the dominant role of topographic and hydrological factors in the region’s flood generation processes. Conclusion The findings of this study indicate that integrating the NDFI index, remote sensing data, and machine learning algorithms within the Google Earth Engine framework provides an efficient, rapid, and cost-effective approach for predicting flood-prone areas in arid and data-scarce regions. Among the evaluated models, Random Forest demonstrated the most stable and accurate performance, showing a strong capability in identifying high-risk areas. Therefore, it can serve as a valuable decision-support tool for flood risk management, land-use planning, and mitigation of flood-related damages. The proposed framework is transferable to other regions with similar environmental conditions and can contribute to enhancing regional resilience to flood hazards. https://gisj.sbu.ac.ir/article_106962.html Sustainable coastal management requires awareness of the trend of shoreline changes. Detecting shoreline changes can help identify and analyze the extent of shoreline displacement. By determining the wave and coastal current patterns and their interaction on sediment transport, changes in coastal morphology can be investigated. Shamkhi Ranjbar et al. (1401) have presented an article entitled Detection and investigation of river shoreline changes using remote sensing data. This study investigated the capabilities of IKONOS Sentinel-2A satellite images in extracting river features to identify and investigate changes in the shoreline of the Karun River in two periods between 2006 and 2018. The objectives of the research are: Identifying the factors affecting the change in the course and geometric shape of the riverbed Investigating the extent of the impact of human intervention on the change in the course of the river This research is a field and system research in terms of its applied purpose and in terms of its implementation method, which is carried out as a case study. In this research, the river course plan is extracted through Landsat remote sensing satellite images, and by applying geometric corrections and georeferencing these images in different time intervals, raster information from the river course will be classified in the ARCGIS software according to the times of image acquisition, and then by digitizing the river coastline, the geometric path of the river is drawn in each time period. This digital information is analyzed and examined in AutoCAD and ArcGis software. Method used: Introducing the MIKE numerical model The MIKE mathematical model, which was prepared and developed by the Danish Hydraulic Institute (DHI), is capable of simulating unsteady flows in rivers, estuaries, irrigation networks and other similar hydraulic systems. Results and Discussion of Satellite Image Analysis of the Research In this study, images from Landsat 5 and 8 satellites were used over a 20-year period. The images used were from frames 135-167 and 134, 134-166 of the above satellite and were from August. The sensor of these satellites in Landsat 5 has 7 bands, 6 of which are spectral and 1 is thermal. Two OLI and TIRS sensors are installed in Landsat 8, 4 bands in OLI and 2 bands in TIRS. At this stage, in order to study the changes in the coastline, the intersection of two consecutive classified images was used. The table and map show the land changes in the region from 2000 to 2020. With the help of this information, it is possible to study the relationship between the trends in changes in different classes with each other. In order to monitor the changes in the coastline, the images obtained from the previous stage, which have two classes of water and land and are intersected with each other, are periodically reviewed. During this period, the total length of the coastline has increased from 74,772 meters in 2000 to 77,292 meters in 2020 (an increase of 2,520 meters). The maximum advance of the water class towards land is about 127.5 meters along the coastline and the maximum advance of land towards the water class is about 202.5 meters at the mouth of the Qara Aghaj River. One of the most important graphical outputs of the numerical model is the distribution of the total sediment load, which is the sum of bed and suspended sediments in different directions. The figure shows the total sediment load of the studied coast. According to the results of the model, the maximum sediment load has occurred in the western areas of the Qara Aghaj River and the sediment distribution is also greater in this area. Therefore, special measures, including dredging, must be taken in these areas to ensure water flow. Also, the numerical values ​​of the sediment transport rate in the study area, according to the numerical model, are shown in the table. https://gisj.sbu.ac.ir/article_106993.html Abstract Background and Aims: In Synthetic Aperture Radar (SAR) images, the backscatter value is significantly affected in areas with complex topography. This issue leads to a reduction in the radiometric accuracy of the images and causes phenomena such as foreshortening and layover. Such effects degrade the quality and reliability of information extractable from radar imagery, making their accurate correction essential for scientific applications. In this regard, numerous models have been developed to rectify these effects, which are generally classified into three main categories: models based on the local incidence angle, models based on pixel area correction, and hybrid models. Each of these approaches has achieved satisfactory results in backscatter correction according to its structure and performance. The present study aims to develop a novel model with high accuracy for backscatter correction in Sentinel-1 images, particularly in forested and mountainous regions. Materials and Methods: In this study, a backscatter correction model was developed by combining two different models. First, the RTF (Radiometric Terrain Flattening) model was applied due to its favorable performance in correcting backscatter values in areas with severe topography. However, after applying this model, some areas located behind the elevations, which could not be accurately modeled, were eliminated. Subsequently, the sinusoidal model was applied to the image corrected by the RTF model. Given the suitable performance of this model in correcting backscatter in areas with gentle topography, its application was restricted to pixels with a local incidence angle exceeding 13 degrees. Finally, the pixels eliminated by the application of the RTF model on the descending pass image were replaced with their corresponding values from the ascending pass image. To investigate the generalizability of the proposed model, introduced as the "Improved RTF model", it was implemented not only in the Kheyrudkenar region of Mazandaran province but also in three other areas within the Dalkhani forests. To evaluate the model's performance, two statistical indices variance reduction and the reduction of the regression slope between the local incidence angle and backscatter as well as a tree species classification method were used. Results and Discussion: In the image of the Kheyrudkenar region, the backscatter variance in VV polarization was reduced by 86.1% after correction with the RTF model and by 91.6% after applying the Improved RTF model, relative to the original image. Furthermore, in VH polarization, the variance decreased by 90% following the RTF model correction and by 93.4% with the Improved RTF model. The slope of the regression line between the local incidence angle and backscatter in VV polarization decreased from -0.00201 for the RTF model to -0.00011 for the improved model, and in VH polarization, it was reduced from -0.00033 to -0.00016, indicating a significant reduction in topographic effects. Additionally, the overall accuracy and Kappa coefficient of the tree species classification increased from 47% and 0.18 with the RTF model to 52% and 0.26 with the Improved RTF model, respectively. To assess the model's generalizability, the two statistical evaluation methods were applied to three other regions in the Dalkhani forests. The obtained results also demonstrated a significant improvement in backscatter correction in these areas. Conclusion: The Improved RTF model, by combining the advantages of both the RTF and sinusoidal models and simultaneously utilizing ascending and descending Sentinel-1 imagery, has provided a remarkable improvement in backscatter value correction. This new model not only exhibits higher accuracy than the individual models but also significantly enhances the quality of the corrected images by mitigating the negative effects of topography. Therefore, this method can serve as a powerful tool in research related to the analysis of radar imagery, assisting researchers in achieving more accurate results. https://gisj.sbu.ac.ir/article_107052.html Nowadays, road extraction is one of the most important analyses of remote sensing data. This process involves identifying and separating roads from other natural and artificial features in aerial or satellite images. According to growing demand for accurate and up-to-date information for urban planning, navigation system, traffic management, mapping, and monitoring, automatic and semi-automatic road extraction has become increasingly important. Although several research studies have been performed, there are still several challenges such as the proximity of trees, building shadows, similarity of road and sidewalk, and the presence of cars on roads. In the recent decade, UAV platforms have been successfully applied in remote sensing applications, especially in remote sensing. According to the high spatial resolution of UAV images, they can be used in road extraction with high accuracy. Road extraction methods from 2D remote sensing images are divided into three categories: morphological operation, traditional machine learning algorithms, and deep learning-based methods. Although morphological methods are able to extract road shape features, they usually have little resistance to gaps, light changes, and contrast. Consequently, ML methods are proposed to solve these challenges. In this group, several textural features are manually extracted, and then classifiers are used for the final classification. The critical problem in road segmentation is accurately identifying pixels in an image as being on or off the road (background). The variety of road areas in terms of their location, size, form, and color makes developing effective segmentation algorithms more difficult. Additionally, when trees or buildings are covered by shadow in images, the accuracy of road segmentation is compromised. According to the high potential of the deep learning methods, they have been applied in the road extraction from remotely-sensed image. We propose a framework to segment UAV images semantically, and the extracted roads are also refined by accurate spatial analysis around road boundaries. In this paper, a new post processing method is developed to enhance the result of convolutional neural networks (CNNs) by injection of spatial information. For this purpose, Xception as a powerful deep learning network is implemented to extract road in UAV images. Although, it detects road accurately but there are still false positive and negative pixels in the classification map. Consequently, post-processing step is proposed to decrease FP and FN by using spatial information. Several morphological operators are considered in this step and also road boundaries with their direction are computed. Fusion of the obtained results based on Xception and spatial information of the post-processing stage, significantly improve the road extraction results. The proposed method has been evaluated on NITR and UDD datasets. The obtained results on NITR show that Xception reaches 93.81% where UNet and SegNet achieve 85.97% and 77.11%, respectively. On the UDD dataset, XCeption achieves 91.94% while UNet and SegNet reach 83.19% and 75.67%, respectively. The proposed method can improve the Xception results up to 96.08% and 94.47%. The obtained results show that deep learning method uses spatial information in semantic segmentation, but the visual evaluation of the obtained classification map shows that there still exist misclassified pixels and more spatial analysis is required. Consequently, we proposed a post-processing step containing morphological operations and road boundaries analysis. The results on complex scenes show that the proposed post-processing step improves the recall metric up to 20%, but in less complex areas it improves less. However, some limitations were also observed in the proposed method where the curved or irregular boundaries were not addressed. This indicates challenges in identifying more complex and irregular patterns, which may be due to structural limitations of the model or the inherent complexities of the data. Therefore, it is necessary to investigate and develop methods and optimize the algorithms in future research.