Ali shamsoddini; Bahar Asadi
Abstract
Identifying and mapping crops provides important information for managing agricultural lands and estimating the area under cultivation of crops. This study investigates the importance of red edge bands for segregation of crops including wheat, barley, alfalfa, beans, broad beans, flax, corn, sugar beet ...
Read More
Identifying and mapping crops provides important information for managing agricultural lands and estimating the area under cultivation of crops. This study investigates the importance of red edge bands for segregation of crops including wheat, barley, alfalfa, beans, broad beans, flax, corn, sugar beet and potatoes using random forest method and support vector machine. For this purpose, the time series of Sentinel-1 and 2 images in 2019 from the northwest of Ardabil was called in the Google Earth Engine (GEE) platform. In order to study the performance of spectral and temporal information, plant indices and backscatter information on the crop mapping, different band combinations were examined. Using the random forest feature selection method, important features were identified and introduced as the input of the random forest and the support vector machine classifiers. Random forest provided the best results for all scenarios. The results showed that the addition of red edge wavelengths and red edge-based vegetation indices are more useful than other bands and vegetation indices for mapping barley, beans, broad beans and flax. The best result among different combinations of features was related to the time series of spectral features of Sentinel-2 images fused with the time series of Sentinel-1 images for that the overall accuracy and the kappa coefficient were 84.67% and 82.31%, respectively. Moreover, the results showed that red edge bands and red edge-based vegetation indices are efficient to identify crops from each other.
Zahra Barkhordari; Ali Shamsoddini
Abstract
Due to the limitations of real precipitation measurement and the lack of proper spatial and temporal coverage of rainfall measurement in the country, remote sensing technology with high temporal and spatial resolution is considered as a useful tool for estimating the amount of precipitation phenomenon ...
Read More
Due to the limitations of real precipitation measurement and the lack of proper spatial and temporal coverage of rainfall measurement in the country, remote sensing technology with high temporal and spatial resolution is considered as a useful tool for estimating the amount of precipitation phenomenon and its temporal and spatial changes; however, satellite data are contaminated to the various errors such as uncertainty in sampling, retrieval errors and inherent errors. Therefore, it is necessary to evaluate the accuracy of their precipitation products before using them. In this study, the effectiveness and accuracy of the precipitation products of CHIRPS, TRMM and MERRA satellites were evaluated using statistical methods against the measured data of 222 synoptic stations located in IRAN on a monthly time scale, for the years 2005-2019. The results showed that the TRMM product with RMSE of 23.84 mm performed better compared to other precipitation products, and after that, the MERRA product with RMSE of 30.57 mm has shown a suitable performance compared to the CHIRPS product with RMSE of 35 mm. Also, the examination of POD, FAR and CSI indices showed that the performance difference of three precipitation products is not considerable and all three have a good performance. In general, the results showed that TRMM satellite products can be used as a good substitute for measured data in where there is no synoptic station. It has also matched in terms of indicators.
Nahid Haghshenas; Ali Shamsoddini
Abstract
Normally, images with a high resolution (temporal or spatial) are available, while there is a limitation in accessing images which are simultaneously high spatial and temporal resolution. While, in some applications, access to images with high spatial and temporal resolution is necessary. Therefore, ...
Read More
Normally, images with a high resolution (temporal or spatial) are available, while there is a limitation in accessing images which are simultaneously high spatial and temporal resolution. While, in some applications, access to images with high spatial and temporal resolution is necessary. Therefore, this study was conducted to downscaling MODIS images to Sentinel- 2 spatial resolution by STARFM, ESTARFM and FSDAF spatio-temporal downscaling algorithms in different land cover classes including urban, garden, pasture, agricultural and water classes. The study area was selected with a variety of land covers around the city of Mahabad, Iran. First, the corresponding visible and near-infrared bands in Sentinel- 2 and MODIS were selected and necessary pre-processes such as geometric correction were done on these images. Then, Sentinel- 2 images were simulated using downscaling algorithms. The results indicated the accuracy of downscaling in the urban, garden and pasture classes compared to the agricultural and water classes. So that the ESTARFM, FSDAF and STARFM algorithms averagely showed the coefficient of determination of 88.25, 87.25 and 86.5 for the urban class, the coefficient of determination of 83.75, 83.25 and 80.5 for the garden class and the coefficient of determination of 90.75, 70.5 and 87.5 for the pasture class in all bands
alijafar mousivand; meysam shir mohammad pour; ali shamsoddini
Abstract
Vegetation is a key component of the earth planet, which controls the energy and water exchanges between atmosphere and the Earth surface and plays an important role in the global energy cycles, such as oxygen, carbon dioxide, and water. Monitoring and management of vegetation are done using its biophysical ...
Read More
Vegetation is a key component of the earth planet, which controls the energy and water exchanges between atmosphere and the Earth surface and plays an important role in the global energy cycles, such as oxygen, carbon dioxide, and water. Monitoring and management of vegetation are done using its biophysical and biochemical parameters such as LAI. Leaf area index (LAI) is one of the most important vegetation parameters that used in most of the applications such as water and carbon cycles modeling.Remote sensing in terms of their continuous and extensive cover is a unique tool for generating vegetation variables. Different retrieval approaches have been developed to extract biophysical parameters information from remote sensing data, which is divided into two broad classes, the statistical/experimental approaches and the physical approach. In the present study, the PROSAIL RT model (Radiation Transfer Model) based on the LUT table have been used to retrieve the LAI variable. Ground reference data collected during the SPARC 2003 campaign were also used to evaluate the accuracy of the retrieved variable. To drawback, the ill-posed problem, four categories of cost functions have been used: Information Measurement (IM), Minimum contrast (MC), Angle Measurement (SAM) and Least Square Error (LSE) and used the multiple Best solution instead of Single best solution. The results showed improvement in the LAI estimation of up to 12% for the multi-species canopy.
Nahid Haghshenas; Ali shamsoddini; Hossein Aghighi
Abstract
It is necessary to know about the quantity of urban tree canopy cover due to its role in air and noise pollution reduction, wind prevention, saving rain water, and runoff control. Being expensive and time consuming, the manual extraction of tree canopy has been replaced by remote sensing techniques conducted ...
Read More
It is necessary to know about the quantity of urban tree canopy cover due to its role in air and noise pollution reduction, wind prevention, saving rain water, and runoff control. Being expensive and time consuming, the manual extraction of tree canopy has been replaced by remote sensing techniques conducted on the images, digitally. There are several parameters which must be optimized prior to use of object oriented classification. One of these parameters is Scale affecting the segmentation results, significantly. Scale is usually set by trial and error which is an experimental approach. One of the aims of this study is to optimize Scale parameter, automatically. In addition, after segmentation process based on a proper Scale, it is required to classify the identified segments based on the attributes which are extracted from these segments. In this stage, the selection of suitable classification method fed by the proper attributes is critical. In this research, LiDAR data and aerial image acquired on Vaihingen, Germany, were utilized for segmenting the urban area. In order to identify suitable attributes, random forest feature selection was applied on the attributes derived from the identified segments. Machine learning methods including support vector machine, random forest, and decision tree were compared for classifying the segments based on their suitable attributes into two classes including tree canopy cover and others. The results indicated that Scale of 25 is the best one to segment this area. Also, the tree canopy cover map derived from support vector machine with quality index of 79.90 showed the best performance among different classifiers used in this study.
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.
hamid salehi; Ali shamsoddini; Seyed Majid Mirlatifi
Volume 10, Issue 3 , January 2019, , Pages 123-140
Abstract
Satellites acquire data in low, medium, and high spatial resolutions. Freely-available high temporal resolution images are often acquired in medium (or low) spatial resolution and high spatial resolution images usually suffer from a low temporal resolution or from high costs. Moreover, high spatial resolution ...
Read More
Satellites acquire data in low, medium, and high spatial resolutions. Freely-available high temporal resolution images are often acquired in medium (or low) spatial resolution and high spatial resolution images usually suffer from a low temporal resolution or from high costs. Moreover, high spatial resolution images are prevented to use in modeling of processes such as evapotranspiration due to the lack of thermal bands. Evapotranspiration mapping with a high spatial and temporal resolutions have been always one of the main subjects in the field of remote sensing. Daily evapotranspiration mapping with a 30 meter spatial resolution is the aim of current study. The case study of the research is Amir-Kabir agro-industrial farms. For this purpose, among 36 bands of MODIS image, those being more spectrally similar to Landsat bands were selected. Then, SADFAT and STARFM algorithms were applied on Landsat 8 and MODIS images to simulate visible and infrared bands with daily temporal resolution and 30-m spatial resolution. Afterward, the simulated bands were used as input for SEBAL algorithm to calculate actual evapotranspiration. Comparing the results with the actual evapotranspiration derived from FAO-Penman-Monteith equation indicated a RMSE of 2.53 mm/day and R2 of 0.69. Also, an RMSE of 0.68 mm/day and R2 of 0.94 were derived when the actual evapotranspiration derived from the downscaled bands were compared with that derived from the Landsat-8 bands. Accordingly, these results showed the efficient performance of the downscaling framework proposed in this study.
A Shamsoddini; Sh Esmaeili
Volume 9, Issue 2 , December 2017, , Pages 117-132
Abstract
Differentiating agricultural areas which are not covered by vegetation from bare lands as well as identifying bare lands from urban areas in medium spatial resolution images, e.g. Landsat imagery, are usually difficult and erroneous tasks which lead to the inaccurate classification results. Therefore, ...
Read More
Differentiating agricultural areas which are not covered by vegetation from bare lands as well as identifying bare lands from urban areas in medium spatial resolution images, e.g. Landsat imagery, are usually difficult and erroneous tasks which lead to the inaccurate classification results. Therefore, this study aims to present a new approach to increase the accuracy of the classification. For this purpose, different scenarios were applied based on different input attributes. The input attributes comprised of spectral bands, textural attributes, i.e. grey level co-occurrence matrix (GLCM), and two types of indices including spatial and thermal attributes proposed in this study. Three classification methods, maximum likelihood (ML), artificial neural networks (ANN), and support vector machine (SVM) embedded with different kernels, were applied to examine different scenarios. The results showed that SVM algorithm embedded with Radial basis function (RBF) results in better accuracy, with overall accuracy of 98.81% and Kappa coefficient of 98.25%, when all types of input attributes were combined together. Finally, the variable importance analysis by random forest feature selection indicated that the proposed indices played an important role to execute more efficient classification by SVM.