hossein Nikpey; Mehdi Momeni
Abstract
Drought is an important phenomenon which can be monitored based on weather data obtained from weather stations and remote sensing data. Remote sensing methods have offered significant relative advantages compared to the other methods for monitoring drought . Also , several drought indicators have provided ...
Read More
Drought is an important phenomenon which can be monitored based on weather data obtained from weather stations and remote sensing data. Remote sensing methods have offered significant relative advantages compared to the other methods for monitoring drought . Also , several drought indicators have provided in remote sensing for monitoring drought , but none of the common indicators in remote sensing did not have generalizability of time , climate and altitude and it is necessary the performance quality of these indexes 1) in climates, 2) in altitudinal zoning examined .This study also proved this hypothesis , to identify appropriate indicators in every altitudinal zone , and in every region the index considered the appropriate season to evaluate indexes . In this study , drought indices ,VCI ,VDI ,TCI and TVDI by LST parameter , NDVI and EVI have been evaluated. To evaluate climate and altitudinal indicators , first in the whole country and then in Hamadan province , climate and altitudinal zoning done and drought indexes for different climates and altitude was determined in two forms pixel-based and object-based (polygons) and compared to precipitation data TRMM sensors . The operation of drought indexes were analyzed to drought evaluation by taking account climate type , data acquisition season , altitude and area . The results of this research shows lack of generalizability of all indictors in terms of climate , altitude and time indicators and for example , in pixel evaluating of hot and dry climate , the highest correlation between VCI index and precipitation data was in June and the lowest correlation is in December.
Mohammad Tavosi; Mehdi Vafakhah; Vahdi Moosavi
Abstract
Due to the importance of meteorological data and limitations of data gathering from ground stations, remote sensing can play an important role in the preparation of these data. The purpose of this study was to quantitatively evaluate the Land Surface Temperature (LST) obtained from Moderate Resolution ...
Read More
Due to the importance of meteorological data and limitations of data gathering from ground stations, remote sensing can play an important role in the preparation of these data. The purpose of this study was to quantitatively evaluate the Land Surface Temperature (LST) obtained from Moderate Resolution Imaging Spectroradiometer (MODIS) sensor images for estimating the maximum and minimum daily air temperature in the Taleghan watershed. For this purpose, the maximum and minimum daily air temperature data of three existing ground stations for the period 2009 to 2015 were obtained. Day and night LST and Normalized Difference Vegetation Index (NDVI) values of MODIS were also prepared. The relationships between each of the effective variables and maximum and minimum daily air temperature in ground stations have been extracted using multiple linear regression method. The results showed that there was a significant correlation between maximum and minimum daily temperature of ground stations with day and night LST and NDVI from MODIS sensor. Therefore, these variables were used in regression relationships. The results of validation showed that the established relationships with all effective variables had the most accuracy. Therefore, the best model for estimating the maximum daily air temperature had , NSE and RMSE values of 0.74, 0.74, and +4.7, respectively and for estimating the minimum daily air temperature had 0.71, 0.72 and +2.9, respectively. Therefore, by converting the surface temperature obtained from MODIS sensor images, the air temperature can be estimated with high accuracy on a daily and monthly scales for various studies.
Mehran Dadjoo; Sayyed Bagher Fatemi Nasrabadi
Volume 10, Issue 4 , February 2019, , Pages 55-68
Abstract
Evaluation of the image classification results is very important in the remote sensing projects. So far, many indices have been presented to assess the accuracy of image classification, though Kappa coefficient and Overall accuracy are the most famous ones. Some researchers have criticized these two ...
Read More
Evaluation of the image classification results is very important in the remote sensing projects. So far, many indices have been presented to assess the accuracy of image classification, though Kappa coefficient and Overall accuracy are the most famous ones. Some researchers have criticized these two parameters, and have presented new parameters for evaluation of the classification results. In this paper, the relation between two new accuracy assessment parameters (presented by Pontius & Millones) and traditional accuracy assessment parameters (Overall accuracy and kappa coefficient) is studied. These two new parameters are called “Quantity disagreement” and “Allocation disagreement” which report disagreement between ground truth and classification data. In order to apply the comparative study on the traditional and new disagreement measures, supervised maximum likelihood classification was applied on 57 satellite images with different spatial resolutions. Then, Kappa and Overall accuracy as traditional accuracy parameters and Quantity disagreement and Allocation disagreement as new measures were computed for each classified image and then the correlation coefficients of the both measures were calculated. The results show a high correlation between new parameters and traditional ones in negative direction irrespective the spatial resolution. In this way, the disagreement do not provide new information about the classification results to the user, and only if there is any request for classification error, the new disagreement parameters can be used along with the traditional ones.
Mansoureh Kouhi; Zahra Shirmohammadi aliakbarkhani; Azadeh Mohamadian; Majid Habibi Nokhandan
Abstract
Evapotranspiration is significantly affected by global climate changes as an essential component of both climate and hydrological cycles. Comprehensive analyses of the spatiotemporal changes of ETo enhance the understanding of hydrological processes and improve water resource management. The main objective ...
Read More
Evapotranspiration is significantly affected by global climate changes as an essential component of both climate and hydrological cycles. Comprehensive analyses of the spatiotemporal changes of ETo enhance the understanding of hydrological processes and improve water resource management. The main objective of this study is to investigate and predict the temporal trend and spatial distributions of the mean maximum temperature (Tmax), the mean minimum temperature (Tmin) and reference evapotranspiration (ETo) during 1961-2014, 2021-2050 and 2051-2080 over Khorasan Razavi Province using CRUTS3.23 dataset and the outputs of four CMIP5 climate models. The results were as follows: (i) the ability of CRU dataset in simulating monthly mean of Tmax and Tmin is suitable, (ii) generally, ETo increased from north to south across the province (ii) from 1961 to 2014, annual ETo exhibited an increasing continuous trend across the area under study (iii) the mean annual minimum temperature projected to increase by 1.6 under RCP4.5 and RCP8.5 scenarios during two future periods. During 2051-2080, this variable will have an increase by 3ᵒ C under RCP8.5 scenario. The maximum temperature will increase by 4ᵒ C during the middle future period under RCP8.5 scenario. (v) The difference between mean annual ETo values of two periods was statistically significant in all grid points covering this province. The results showed that these increases may lead to the increase in crop water requirements and aggravate the water shortage in this area in view of the increase in ETo in response to ongoing climate change.
Volume 6, Issue 1 , April 2014
Abstract
Secchi disc is an indicator of the clarity of the water bodies. In this study, new univariate and multivariate linear regression models are developed for monitoring of Secchi disc depth (SD) in the Caspian Sea using MERIS images and unlike of previous studies, the developed models are tested to determine ...
Read More
Secchi disc is an indicator of the clarity of the water bodies. In this study, new univariate and multivariate linear regression models are developed for monitoring of Secchi disc depth (SD) in the Caspian Sea using MERIS images and unlike of previous studies, the developed models are tested to determine the real accuracy of developed models for the Secchi depth monitoring. In situ measurements of Secchi disc depth was performed in the southern part of Caspian Sea between July and October 2005 and consequently, 25 training and 12 testing data were acquired. In this study, 25 Level 1B MERIS images of the Caspian Sea, acquired concurrent with in-situ measurements, were employed. In univariate regression, the correlation between Secchi depth and Spectral reflectance data (Rrs) and the ratio of Rrs data were investigated and then the Secchi depth and the Rrs parameters with high correlation coefficient were selected and some univariate models were fitted using the training data on them. In addition, the appropriate multivariate regression models were developed using Cp mallow’s statistics and the best one was selected by the test data. The results showed that the developed multivariate model presents better results than univariate models and it has higher correlation coefficient than the previous studies. The variables of the best multivariate model were the reflectance in 412, 510, 560, 681, 779 nm and the correlation coefficient and percentage error of the best model were about 0.7 and 37.7 %, respectively. Finally the maps of Secchi depth in the Caspian Sea were retrieved using the developed multivariate model.
Volume 6, Issue 2 , August 2014
Abstract
In this research, a model for simulating of residential segregation pattern is presented via integration of GIS with agent-based models, and is implemented on real data of an area in north-west of Tehran. For this purpose, at first effective parameters regarding segregation in Tehran that is a mixture ...
Read More
In this research, a model for simulating of residential segregation pattern is presented via integration of GIS with agent-based models, and is implemented on real data of an area in north-west of Tehran. For this purpose, at first effective parameters regarding segregation in Tehran that is a mixture of social-economical factors and environment was determined and amount of their effects with AHP method was set. Considering the raster-based approach in modeling, maps related to these parameters was produced in ArcGIS medium. By programming in Netlogo software the mentioned model was developed .In this model, with a primary assumption, people of society were classified in 4 socio-economic groups with specific attributes and behaviors which by their own decisions- micro level actions- affect the segregation pattern- effects in macro level-. The pattern of urban segregation of area was simulated for a period of 20 years between 1986 and 2006. The model was calibrated by changing the important parameters of Schelling model, neighborhood radius and frequency of the same type neighborhoods, and some other parameters as size of pixels, price of parcels, rate of population increase etc. Validation of the proposed model has been done by counting the correct estimated pixels of total pixels. Respectively 62.5 % verifies the accuracy of the models. Keywords: GIS, Residential Segregation, Agent Based Model, Simulation.
Volume 6, Issue 4 , October 2014
Abstract
Using new approaches to optimize the process of power transmission line routing can solve many complex problems which power transmission line routing decision-makers are faced. Due to the expansion of involved parameters we can consider multi-objective evolutionary algorithms as appropriate method in ...
Read More
Using new approaches to optimize the process of power transmission line routing can solve many complex problems which power transmission line routing decision-makers are faced. Due to the expansion of involved parameters we can consider multi-objective evolutionary algorithms as appropriate method in this area. In this thesis with using multi-objective evolutionary algorithms NSGA-II and offered suitable genetic operators, the power line routing has been optimized. In consultation with experts in Ministry of Energy and Mazandaran Regional Electric Company, it was designed three objective functions to build routs with following characteristics: F1-Minimum cost, F2- Minimum environmental and social effectsand F3- easy accessibility and maintenance of transmission lines. Implementation and evaluation of developed model embed in Geospatial information system (GIS) represent that model have high capability to optimize the objective functions. This model tested and evaluated in Mazandaran province-IRAN, between two power-post 400KV Hasankeif (in Kelardasht City) and Narivaran (in Amol City). The obtained result shows a 15 percent improvement on average in objective function compared with the existing power transmission line. Keywords: Routing, Power transmission, NSGA-II, GIS.
Volume 6, Issue 3 , October 2014
Abstract
Geothermal energy serves as a renewable and clean energy. Thanks to its great advantages such as relatively harmless, low costs and environmental friendly, it may be a good substitute for fossil fuels. In the present study, a geothermal survey is conducted in an area prone geothermal Ferdows of South ...
Read More
Geothermal energy serves as a renewable and clean energy. Thanks to its great advantages such as relatively harmless, low costs and environmental friendly, it may be a good substitute for fossil fuels. In the present study, a geothermal survey is conducted in an area prone geothermal Ferdows of South Khorasan province in eastern Iran using ETM+ data Landsat 7 geo-referenced to topography map in scale 1:50000 of Ferdows city. Pixel number of thermal bands was converted to spectral radiance and then radiance temperature was measured. NDVI index was calculated from the visible bands in and near infra-red bands and subsequently radiance potential layer obtained. Earth surface temperature was determined by integrating both reflective and radiative temperatures. The method of least squares fitting, was used to produce layered zones of iron oxides and clay minerals and regions faults was extracted from map in scale 1:100.000. Through integration of produced layers using weighted overlapping method, geothermal prone area in Ferdows city was recognized. The potential geothermal of Ferdows in east part of Iran were evaluated and identified with the key factors associated with the formation of geothermal resources. Synthesizing the information layers, prone areas in order to geothermal energy utilizing were recognized. Hence, two resources of geothermal energy within the area were identified, which is spatially correlated with geothermal evidences such as hot spring and two inactive volcanoes. Based on the outcomes of this research, the remote sensing approaches are cost effective for determining surface temperature anomalies and area geological features such as alterations and rock units’ identification. Combining TIR remote sensing with geological analysis and the understanding of geothermal mechanism is an accurate and efficient approach to geothermal area detection. Keywords: Remote Sensing, Geothermal Energy, Land Surface Temperature, Landsat.
Mohsen Ebrahimi; Zohre Ebrahimi-Khusfi
Abstract
The Central Plateau of Iran, due to climate changes and the reduction of available water resources on one hand, and the increase in population and the consequent increase in demand on the other hand, is facing a severe water crisis. The science of remote sensing and the availability of numerous satellite ...
Read More
The Central Plateau of Iran, due to climate changes and the reduction of available water resources on one hand, and the increase in population and the consequent increase in demand on the other hand, is facing a severe water crisis. The science of remote sensing and the availability of numerous satellite products have made it possible to monitor the process of changes in various environmental parameters, especially surface and underground water sources, with appropriate accuracy. For this purpose, using the Google Earth Engine system, 16 different satellite products including different environmental parameters such as precipitation, temperature, evaporation and transpiration, soil moisture, runoff, total water storage (GRACE), vegetation cover index and water surface area were received and prepared for the time period 2000-2022. Then, using the non-parametric Mann-Kendall test and the Sen’s slope estimator, the change trend of these parameters was investigated. According to the results, the changes in earth's gravity, which indicates the level of underground water, as well as the area of water surfaces, which indicates surface water resources, and soil moisture, showed a significant decreasing trend. On the other hand, maximum temperature, minimum temperature, potential evaporation and transpiration and NDVI index have a significant increasing trend. Despite the decrease in water surface area, the vegetation cover index has increased, which indicates the increase in the area under cultivation of agricultural products and excessive harvesting of underground water resources, which is also confirmed by the decreasing trend of the GRACE satellite product. The correlation coefficients between parameters with significant trends also showed that there is a significant correlation between GRACE and NDVI parameters, minimum temperature, maximum temperature, soil moisture and area of surface water bodies.
M.R Mobasheri; E Amraie
Volume 7, Issue 4 , November 2015, , Pages 45-60
Abstract
Detectors noises in satellite images are seen as either vertical or horizontal stripes. The directions of these stripes depend on the imaging technique (Pushbroom or Wiskbroom). The main reasons in appearance of stripe noises in TM images are; lack of matching between detectors, unsuitable calibration ...
Read More
Detectors noises in satellite images are seen as either vertical or horizontal stripes. The directions of these stripes depend on the imaging technique (Pushbroom or Wiskbroom). The main reasons in appearance of stripe noises in TM images are; lack of matching between detectors, unsuitable calibration and detector degradation in time. Due to the Wiskbroom technique in TM sensor, the stripes appear horizontally. Among these, the stripe noises in band4 are more profound in images acquired from dark surfaces such as sea surface. This kind of noise may produce sever errors in atmospheric correction based on dark surfaces. In this work, to correct the stripe noise, Mean Method (MM), Modified Spatial Momentum Matching (MSMM), and image filtering in frequency and spatial domain (IFFD & IFSD) are introduced. To evaluate the results, some statistical parameters such as averaging, standard deviation, histograms and Fourier spectrums before and after corrections are deployed. Reduction in standard deviation after denoising demonstrates enhancement in the image. To compare these methods with other known methods, parameters such as MSE, RMSE and PSNR along with simulated images for periodical striped noise are used. Among these, the maximum PSNR and naturally the minimum MSE belongs to MM and MSMM methods and consequently these methods perform better accuracies compared to IFFD and IFSD.
Z Ghaemi; M Taleai; M Farnaghi; G Javadi
Volume 9, Issue 3 , February 2018, , Pages 45-70
Abstract
Urban growth and increased use of vehicles have led to an increase in air pollution, especially in large and industrialized cities in recent years. Because of the adverse effect of air pollution on human and other creatures, prediction and modeling of this complex phenomenon have the main concern of ...
Read More
Urban growth and increased use of vehicles have led to an increase in air pollution, especially in large and industrialized cities in recent years. Because of the adverse effect of air pollution on human and other creatures, prediction and modeling of this complex phenomenon have the main concern of researchers during the last years. The purpose of this research is to design an air pollution prediction system to identify the contaminated areas in order to help the urban managers and planners to control and reduce the amount of contaminants. In the proposed system in order to predict the air pollution in different seasons, PCA-ANFIS model has been used. In this system, meteorological data and concentrations of pollutants are used to predict air pollution in Tehran over the next 24 hours. In addition, spatial parameters including height, topography and distance from the road are used to model the spatial distribution of air pollution. Comparing the results of PCA-ANFIS and ANFIS methods prove that the proposed model obtained higher accuracy in less processing time.
Arash bihamta; Hamid Goharnejad; saber moazami
Volume 10, Issue 2 , September 2018, , Pages 45-60
Abstract
Rainfall is the most important factor directly involved in the hydrological cycle. Obtaining accuraterainfall data is essential for analyzing various hydrological phenomena and climate change. The aimof this study was to investigate the accuracy of the rainfall data of two GPM satellites with IMERGand ...
Read More
Rainfall is the most important factor directly involved in the hydrological cycle. Obtaining accuraterainfall data is essential for analyzing various hydrological phenomena and climate change. The aimof this study was to investigate the accuracy of the rainfall data of two GPM satellites with IMERGand TRMM with 3B42 product at four synoptic stations in Tehran on daily, monthly and seasonalscales. In comparative comparison between satellite data and rainfall observation data CorrelationCoefficient (R), Bias, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), with the aimof validating data, and Probability of Detection (POD), False Alarm Ratio (FAR) and Critical SuccessIndex (CSI) verification of the data were investigated. The results showed that the correlation betweenIMERG data and rain observation data at station is higher than 3B42 data. In addition, the Bias, MAEand RMSE values confirmed that both the 3B42 and IMERG products had the lowest error rates withobservation data. Also, In the evaluation of the IMERG product with rainfall values of the Shemiranstation, the correlation at this station on the daily, monthly and seasonal scale was 57%, 83% and87%, respectively. In general, considering to its superior technology, IMERG has a high precision anda good tool for hydrological forecasting.
Kazem Aliabadi; omid baghani
Abstract
This study aims to provide a computational-approximate algorithm based on Rationalized Haar (RH) to estimate the vegetation of the Landsat image using reflecting this phenomenon in the near-infrared band. This band is in the RGB color combination and located in the R section.This algorithm, using Digital ...
Read More
This study aims to provide a computational-approximate algorithm based on Rationalized Haar (RH) to estimate the vegetation of the Landsat image using reflecting this phenomenon in the near-infrared band. This band is in the RGB color combination and located in the R section.This algorithm, using Digital Number (DN) vegetation in 200 selected pixels of R band (infrared band) from the study area, tries to extract the features and vegetation of the whole study area. The number of selected pixels is distributed uniformly and only covers the vegetation.Due to using the matrix format in the input data, first vegetation reflection matrices for 4 and 8 wavelets are constructed using the assumed 200 pixels. Then, these matrices are extended to 16 and 64 parts respectively, through blocking the Landsat image of the region.Each matrix element represents the average vegetation of the area in its corresponding block. Then, by introducing an efficient mathematical equation, the vegetation of the entire study area is extracted. In addition, each pixel is reconstructed. Due to matrix calculations, speed and accuracy of calculations at the pixel scale will be listed as advantage of this approach.In this study, vegetation extraction with 4 and 8 RH Wavelets was performed with 75 and 87.5% accuracy, respectively. As the number of wavelets increases, the accuracy of the RH wavelet algorithm increases. However, rounding error and the increase in computational cost in high number of wavelet can be listed as disadvantage of this method. Such that, time and space memory will be increased exponentially. In remote sensing, extraction techniques such as classification have been proposed by remote sensing software. The accuracy of vegetation pixel extracted using this approach will be as advantage in comparison with those common methods. In processing and analytical techniques (for vegetation extraction and classification) in remote sensing, many pixels contain vegetation depicted as single or clustered (but in small numbers) while, in other classes such as barren or Urban land will be merged, which RH wavelet overcomes this shortcoming.
Elham Mehrabi Gohari; Hamid Reza Matinfar; Azam Jafari; Ruhollah Taghizadeh-Mehrjardi; F khayamim
Abstract
Visible and Near-Infrared (VNIR) and Short-Wave Infrared (SWIR) reflectance spectroscopy (400-2450nm), which are at least as costly and time-consuming, are widely used in the estimation of physical and chemical properties of the soil. The purpose of this study was to investigate the ability of this method ...
Read More
Visible and Near-Infrared (VNIR) and Short-Wave Infrared (SWIR) reflectance spectroscopy (400-2450nm), which are at least as costly and time-consuming, are widely used in the estimation of physical and chemical properties of the soil. The purpose of this study was to investigate the ability of this method to estimate the amount of organic matter, carbonates and gypsum content of soil surface. In the present study, 115 profiles were identified based on the Hypercube technique, and the horizons were sampled and the amount of organic matter, carbonates and gypsum content were measured by standard methods. Reflectance spectra of all samples were measured using an ASD field-portable spectrometer in the laboratory. Soil samples were divided into two random groups (80% and 20%) for calibration and validation of models. PLSR and PCR models and different pre-processing methods i.e. First (FD) and Second Derivatives (SD), Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV) were applied and compared to estimate texture elements. The highest RPD of calibration and validation were obtained for PLSR with First derivative of reflectance+ Savitzky_Golay filter pre-processing technique which was classified as a good for the amount of organic matter and gypsum and was classified as a poorly for the amount of carbonates.
Behzad Mohammadi Sheikh Razi; Mohammad Sharif Molla; Ali Jafar Mousivand; Ali Shamsoddini
Abstract
< p >Vegetation biophysical and biochemical variables are key inputs to a wide range of modelling approaches for carbon, water, energy cycle, climate and agricultural applications. Leaf Area Index (LAI) is among the most important canopy variables, used by many different physiological and functional ...
Read More
< p >Vegetation biophysical and biochemical variables are key inputs to a wide range of modelling approaches for carbon, water, energy cycle, climate and agricultural applications. Leaf Area Index (LAI) is among the most important canopy variables, used by many different physiological and functional plant models. Several approaches have been developed for vegetation properties retrieval from remotely sensed hyperspectral data. Among them, nonparametric machine learning methods have increasingly gained attention in vegetation variable retrieval due to their flexibility and efficiency while working with data of high dimensionality over the last decades. Although these methods provide reasonable accuracy at relatively high speed, they are mainly restricted to estimate values within their training domain and often perform poorly on the marginal values (i.e. outside of the training domain). The performance of these methods has not been adequately studied in retrieving LAI on the marginal values. This study employs four well-known machine learning methods including SVR, GPR, ANN, and RF to retrieve LAI from a hyperspectral CHRIS-Proba image over Barrax, Spain, in order to inspect their capability in retrieving marginal values. The results showed that although all the methods perform similarly well on retrieving LAI over the training domain values with RMSE values of less than 0.5 and relative error of less than 10%, GPR and SVR performed slightly better. However, ANN outperformed the other methods in estimating LAI on the marginal values, resulted in the generated LAI map more consistent with the NDVI map, as well as, the hyperspectral image of the region.
MayamSadat Ahmadi; Abbass Malian
Abstract
The design of Remote Sensing algorithms and the development of various methods of processing satellite images to identify porphyry copper deposits are among the important topics of studies in the field of mineral resource evaluation and their optimal exploitation. To this end, the determination of alteration ...
Read More
The design of Remote Sensing algorithms and the development of various methods of processing satellite images to identify porphyry copper deposits are among the important topics of studies in the field of mineral resource evaluation and their optimal exploitation. To this end, the determination of alteration zones provides a suitable tool for designing acceptable exploratory patterns. In this research with an almost comprehensive strategy and using the determination of alterations related to porphyry copper deposit based on Lowell and Gilbert model with three different strategies (visual, spectral and statistical processing) as well as the extraction of linements in the case area The study suggested the concentration range of the mineral for drilling. The study area in this article is Masjed Daghi porphyry copper deposit in the northeast of East Azerbaijan province, which consists of multispectral satellite images of ASTER, OLI of Landsat-8 and Sentinel-2 sensors for various processes including band ratio combinations, principal component analysis and pixel and subpixels basics spectral processing methods including SAM and MTMF, and statistical processing using the logical operator algorithm. Finally, by fuzzy and combining the layers of satellite image processing with geometric structures of the region (linements) which were extracted on Sentinel-2 data in two automatic and semi-automatic methods, the results were analyzed in GIS space and by comparing the presented results with the analysis of ground samples, the accuracy and conformity of the target areas were confirmed. User and producer accuracy for the area with the first priority were 78.54% and 78.36%, respectively, which are more appropriate criteria for introducing the area of the drilling center.
nima farhadi; Abas Kiani; Hamid Ebadi
Abstract
Object detection is one of the fundamental issues in image interpretation process, especially from remote-sensing imagery. One of the most effective and efficient methods in this field is the use of deep learning algorithm for feature extraction and interpretation. An object is a collection of unique ...
Read More
Object detection is one of the fundamental issues in image interpretation process, especially from remote-sensing imagery. One of the most effective and efficient methods in this field is the use of deep learning algorithm for feature extraction and interpretation. An object is a collection of unique patterns that differ with own adjacent properties. This difference usually occurs in one or more features simultaneously, which can be indicated by the difference in shape, color, and gray values. In this regard, the use of deep learning as an efficient branch of machine learning can be useful in generating high-level concepts through learning in different layers. In this research, a database based on the environmental and geographical conditions from some Iranian airports was created. Additionally, an optimal learner model was developed with a convolutional neural network. For this purpose, in the raw data processing section, besides using the transfer learning method, some vectors were extracted to classify the objects and delivered to an SVM model. The output values were compared with the values obtained from the test image for each object, and they were analyzed in a repeatable process for structural matching. Precision of 98.21% and F1-Measure of 99.1% was achieved, for identification of the target objects
Alireza Ramezani Khojeen; Mir Masood Kheirkhah Zarkesh; Peyman Daneshkar Arasteh
Volume 7, Issue 3 , November 2015, , Pages 49-64
Abstract
Calculating the canopy temperature and land surface temperatureusing satellite imagery is very attractive to estimate actual evapotranspiration (ET) by energy balance algorithm. In studies, to evaluate ET, the accuracy of the calculated thermal gradient between surface and air, as well as temperature ...
Read More
Calculating the canopy temperature and land surface temperatureusing satellite imagery is very attractive to estimate actual evapotranspiration (ET) by energy balance algorithm. In studies, to evaluate ET, the accuracy of the calculated thermal gradient between surface and air, as well as temperature difference between various land covers is very important. To calculate land surface temperature (LST) in Shahr-E-Kord plain, the study area, there were three principal challenges. First, the absence of enough studies about calculating LST using Landsat8 thermal bands, the second, lack of canopy temperature and land surface temperature observed data, and finally, the only available data for surface temperature was minimum daily surface temperature in the climatology and synoptic stations. In this study, in order to convert the surface brightness temperature to the LST, the split-window algorithm of NOAA-AVHRR was used. Also, the proposed SEBAL algorithm was applied to calculate the surface emissivity. Due to the lack of the reference weather stations, after calculating LST at the satellite overpass time in non-reference weather stations, the deviation error calculation method was used to calibrate satellite LST and to prepare daily LST layers. Results showed that all calculated correlation coefficients were more than 0.9. Also, all existing regression relations were significant at 95% and even 99% level of confidence. In different day-images, maximum difference of calculated deviation errors was less than 0.5 K and, the calculated RMSEs were between 1.9 to 2.2 K, acceptable comparing to similar studies.
, A.A Torahi; M FiroziNejad,; , A Abdolkhani
Volume 9, Issue 1 , October 2017, , Pages 49-62
Abstract
Obtaining more accurate and updated information about the forest area is one of the basic factors in sustainable management of this area. Acquiring this information is more beneficial in terms of time and cost through classification of remote sensing data. In this paper, Landsat8 (OLI) data from Maroons ...
Read More
Obtaining more accurate and updated information about the forest area is one of the basic factors in sustainable management of this area. Acquiring this information is more beneficial in terms of time and cost through classification of remote sensing data. In this paper, Landsat8 (OLI) data from Maroons Behbahan riparian forest that is located in Khoozestan province of Iran were used for mapping and better management of riparian forest. Preprocessing operation including radiometric and atmospheric correction was applied to the data. Supervised classification algorithms including maximum likelihood (MLC) and support vector machine (SVM) with seven and three classes were used for classification. In order to evaluate the capability of support vector machine, three categories of training data with 241, 141 and 41 numbers with four kernels of SVM (linear, radial basic function, sigmoid and polynomial) were used. The results indicate that mapping of Maroons riparian forest using Landsat images is possible and the best result was acquired using SVM –polynomial method by three classes with overall accuracy and kappa coefficient of (99/24) % and (0/97) respectively. Also, the findings showed that with reduction of number of classes from seven to three, the accuracy of classification is increased. By reducing the number of samples to moderate, significant difference in accuracy of classification was not observed, but by more reduction of samples, the accuracy of results is reduced.
Hamidreza Matinfar; foziyeh kohani; Ali Akbar Asilian mahabadi
Abstract
Soil salinity is one of the most important environmental problems, and the identification and zoningof saline soils is difficult due to the need for sampling and laboratory analysis, as well as havingtemporal and spatial variability. In recent years, the use of satellite imagery has always been ofinterest ...
Read More
Soil salinity is one of the most important environmental problems, and the identification and zoningof saline soils is difficult due to the need for sampling and laboratory analysis, as well as havingtemporal and spatial variability. In recent years, the use of satellite imagery has always been ofinterest to experts due to its ease of use and ability to detect phenomena. Remote sensing informationgreatly aids the study of soil salinity and can be helpful in identifying salinity values. In this study,220 soil samples were collected from Meymeh area of Dehloran, south of Ilam province, according tothe type of study and physiographic types and soil units. Then, pH and EC values were measuredusing standard methods. Soil salinity values were evaluated using correlations between EC electricalconductivity values obtained from ground data and variables obtained from Landsat 8 satellite imagesincluding bands, salinity indices, vegetation indices and soil indices. Finally, the soil surface salinityestimation model was obtained using stepwise regression method. This method involves the automaticselection of independent variables, and with the availability of statistical software packages, it ispossible to do so even in models with hundreds of variables. In previous studies, indicators and bandshave been used separately and in a limited way, but in this study, an attempt has been made to use acombination of different indicators more widely, and finally to achieve the best relationship byeliminating the indicators that have the least impact on soil salinity estimation. Using significant levelanalysis and correlation between the output of models and ground data, the best model with a value of(R2 = 0.882) was selected and a soil salinity map was prepared based on it. In the study area, thehighest area belonged to non-saline class which comprises 75% of the total study area and about 1%of the soils belong to the saline class.
Mohammad hossein Gholizadeh; Jamil Amanollahi; Fardin Rahimi
Abstract
The aim of this study was to evaluate the accuracy of MODIS satellite data in monitoring aerosol (PM10 particles) to compare with ground pollution station data It was done in Sanandaj. In this case, the performance of satellite data in measuring dust particles at Sanandaj ground station is identified. ...
Read More
The aim of this study was to evaluate the accuracy of MODIS satellite data in monitoring aerosol (PM10 particles) to compare with ground pollution station data It was done in Sanandaj. In this case, the performance of satellite data in measuring dust particles at Sanandaj ground station is identified. At first, the aerosol optical depth data provided by MODIS sensor was prepared based on the corresponding of the PM10 measured by pollution monitoring station located in Sanandaj.Then, the correlation coefficient between two series of data was calculated. In order to obtain the accurate prediction of PM10 the ARIMA and artificial neural network were used.The AOD of MODIS sensor was combined using maximum likelihood and root mean square error for input of prediction models. At last, a single comparison method for each model as well as models comparison was evaluated to identify the accurate model in predicting of PM10. In the ANN model R2 was acquired in training phase as 0.52, and testing phase as 0.53 with RMSE=1.62 and MAE=2.62. The analysis showed that the ARIMA model 1-0-3 with R2=0.46, MAE=0.06 and RMSE=0.69 is the only acceptable model.It states that ARIMA model, is a suitable model for prediction of PM10. However, the ANN model was more accurately estimated for the correlation between the data.The results of presented study showed that there is direct relationship between the MODIS sensor AOD data and ground station PM10 data.The results conclude that this algorithm is capable for detecting of dust and can be good alternative to the PM10 provided by the ground stations measurement.
F Taghavi; A Ahmadi; Z Zargaran
Volume 8, Issue 2 , November 2016, , Pages 53-72
Abstract
In this study, a combined model of modular networks and satellite image processing and optimization algorithms to forecast land surface temperature in an area including city of Tehran is presented. Calculating the LST has been done based on brightness temperature features in 31 and 32 MODIS channels. ...
Read More
In this study, a combined model of modular networks and satellite image processing and optimization algorithms to forecast land surface temperature in an area including city of Tehran is presented. Calculating the LST has been done based on brightness temperature features in 31 and 32 MODIS channels. Thus, brightness temperature data related to these images is fed to neural network and values of land surface temperature are recovered as the output of the network. In this way,after obtaining the optimal structure obtained for networks they are trained and their weights are extracted. Then by applying a neural network with a modular structure and clustering algorithms, training will be also modular. Decomposition of the networks and after that combining the results to get the final forecast makes the performance of the modular network more effective. As a result , a new approach based on the combination of neural network or self-organizing map and particle swarm optimization algorithms is proposed. The results showed that using PSO algorithm causes appropriate distribution of cluster of SOM method and using satellite images improved performance of the proposed model. Finally, results are compared with training neural network models and non-modular structure. The results of this comparison show that model-training time in predicting the land surface temperature is decreased and the accuracy of model increased. The little difference between the predicted values and actual (real) values of temperature in the region shows that this model could predict the temperature accuraetly, so that, in this hybrid model Mean Square Errors (MSE) and Mean Absolute Percentage Error (MAPE) are 0.0081 and 10.59 respectively.
Farzaneh hadadi; Mohsen m_azadbakht; Maedeh Behifar; Hamid Salehi Shahrabi; amir moeinirad
Volume 10, Issue 3 , January 2019, , Pages 53-76
Abstract
Over the past several decades, many vegetation indices have been developed for crop yield estimation, each being sensitive to different levels of crop density and leaf area index, based on the bands and the algebraic formulas used in its design. However, the study of some perennial crops such as alfalfa, ...
Read More
Over the past several decades, many vegetation indices have been developed for crop yield estimation, each being sensitive to different levels of crop density and leaf area index, based on the bands and the algebraic formulas used in its design. However, the study of some perennial crops such as alfalfa, which are harvested several times annually, is very complicated and has received less attention. Therefore, in this paper, the most important vegetation indices developed to estimate alfalfa yield are using Sentinel-2 time series images. In this research, 144 alfalfa samples were collected periodically in a destructive way from alfalfa farms of Magsal Agricultural and Production Company (Qazvin) near the time of satellite pass, and then the efficiency of 10 of the most famous vegetation indices to estimate alfalfa yield was evaluated based on Sentinel-2 images. The results of this research showed that the estimated alfalfa yield using the index had the highest correlation () and the lowest root-mean-square-error (RMSE = 0.316 ) compared to the field data collected in the middle of August. In addition, the results showed that the red edge indices did not solve the saturation problem of vegetation indices and that the green vegetation indices were more capable of estimating alfalfa yield than the red edge indices.
ali khedmatzadeh; Mir Najaf Mousavi; Hojjat Mohammadi Torkamani
Abstract
The growth of the urban population has been led to increasing of the urban spaces and growth of the city size. as a result of further construction and alteration of the land available to the benefit of its built-up spaces. Special location the city of Urmia at proximity of the Urmia lake and unfavorable ...
Read More
The growth of the urban population has been led to increasing of the urban spaces and growth of the city size. as a result of further construction and alteration of the land available to the benefit of its built-up spaces. Special location the city of Urmia at proximity of the Urmia lake and unfavorable condition of this lake reveals the necessity of the proper landuse planning at this city. One of the required tools for proper planning in this field is the use of remote sensing techniques. The present study aims to evaluate these changes (period 1989-2015) and predict its future trend. SVM and neural network methods are used to evaluate changes in 5 classes Due to the high accuracy of the classification of the neural network, the results of this classification have been used to predict changes for the 2045 horizon. Land constructed in 1989 is 7469.1 hectares, reaching 9217.3 and 94366.9 hectares in 2002 and 2015 respectively, and by2045, according to the prediction model, the neural network is equal to 22449.6 hectares, which is built on lands 13012.7 Shows hectares of increase. The determination coefficient (0.73) and rock curve (82.55%) also indicate the high accuracy of the neural network model to predict urban development changes. The Heldern method results shows that all of these constructions are not based on the real needs of the city And the sparse phenomenon has happened.
F Sarmadi; H Ebadi; A Mohammadzadeh
Volume 7, Issue 2 , November 2015, , Pages 55-68
Abstract
Determination of land use and land cover changes is necessary for monitoring of urban growth and responsible urban planning. Remote sensing can be used as a powerful technology in land use and land cover change detection. One of the challenges in this area is to developing efficient methods for accurate ...
Read More
Determination of land use and land cover changes is necessary for monitoring of urban growth and responsible urban planning. Remote sensing can be used as a powerful technology in land use and land cover change detection. One of the challenges in this area is to developing efficient methods for accurate and highly automated change detection which can produce accurate and precise information about position and content of the changes. In this study two GeoEye images from Tehran 17th region related to 2004 and 2010 years were used. This study Proposed a method based on image context spatial features, neural networks and genetic algorithm. Six cases with direct multi-date classification approach and post classification approach were implemented and compared in the viewpoints of accuracy and runtime. Direct multi-date classification was superior in all six cases. Between six implemented cases, sixth case (proposed method of this research) was superior in the classification accuracy point of view. In this case after selecting optimized features, ANN classification was executed based on determining architecture and several times execution. Though runtime of sixth case was the highest, if accuracy is prior, it’s highly recommended.
