Reza Shahhoseini; Kamal Azizi; Arastou Zarei; Fatemeh Moradi
Abstract
Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements that are essential for decision-makers. Therefore, the accuracy of maps obtained from the classification of satellite images is very effective in uncertainty for urban management. Due to the ...
Read More
Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements that are essential for decision-makers. Therefore, the accuracy of maps obtained from the classification of satellite images is very effective in uncertainty for urban management. Due to the uniform quality of images in large areas at regular intervals, remote sensing images are essential for land use maps. The primary purpose of this study is to present a proposed method to create an accurate land cover map in urban areas using a combination of Sentinel-1 and Sentinel-2 data. For this purpose, the features of the backscattering coefficient VV and the two parameters obtained from the H-α decomposition method (entropy, alpha) of Sentinel-1 radar images and the features of the blue, green, red band, NDVI, NDWI, MNDWI, and SWI were extracted from Sentinel-2 Multispectral images and used as influential components to classify the urban area. To separate agricultural areas from other coatings, the SWI index was used. Elevation data have also been used to optimally distinguish complex classes with different topographies. We evaluated the extraction of effective indicators from these two datasets in an object-oriented approach based on support vector machine algorithms and random forest for land use classification. The results showed that using properties extracted from radar and Multispectral images simultaneously in the object-oriented classification method could altogether determinate the object's properties in the study area. When optical and radar data were used simultaneously for both classification algorithms, the overall accuracy classification increased. For the stochastic forest method, which provided the highest accuracy, the overall accuracy for the radar and optics data combination approach increased by 13% and 5%, respectively, compared to the radar feature approach and the optics feature approach alone. There was also a significant difference in classification accuracy at all levels between the support vector machine classification algorithm and the random forest. The results showed that the random forest classification method's overall accuracy and support vector machines were 83.3 and 79.8%, respectively, and the kappa coefficient was 0.72 and 0.68%, respectively.
Mohammad Saadat; Reza Shahhoseini
Abstract
Preparation of proper land use maps has always been one of the important goals of researchers and policymakers. The aim of this study was to provide a new method for preparing land use maps using remotely sensed data and satellite data imagery. For this Purpose, we used Landsat 8 data, Digital Elevation ...
Read More
Preparation of proper land use maps has always been one of the important goals of researchers and policymakers. The aim of this study was to provide a new method for preparing land use maps using remotely sensed data and satellite data imagery. For this Purpose, we used Landsat 8 data, Digital Elevation Model (DEM), Principal Component Analysis (PCA), and Spectral Indices to extract land use map in the study area. After all required preprocessing, the training samples were provided. In this study, the training samples were utilized in two parts; in the first part they were used as inputs for image classification using supervised algorithms of maximum likelihood Classification (MLC) and support vector machine (SVM). In the second part, in order to applying Decision Tree Classification (DTC), these training samples were used to determine the spectral reflection of each end-member in the spectrum of electromagnetic waves (image bands, PCA, spectral indices, and DEM).Then, using these binary data and DTC, each end-member was identified and the Landuse/Landcover (LULC) map was extracted. In order to combine the classification results and achieve higher accuracy, the Majority Vote Classification (MVC) method was applied to prepare a new compilation of land use in the area. In order to evaluate the accuracy of produced maps, the statistical parameters extracted from the confusion matrix including overall accuracy, kappa coefficient, user and producer’s accuracy were utilized. According to the results, the combined method (MVC) with a total accuracy of 93.37% and kappa coefficient of 0.91 had the highest accuracy. The overall accuracy of the DTC, SVM, and MLC were 89.61, 88.01 and 87.6%, respectively. Due to the fact that in the nature most of the landuse are mixed and complicated, it would be better to use new methods that cover all aspects of the phenomena. In this research, the data extracted from the supervised classifications as well as the data derived from the DTC were combined and the results clearly illustrate the improvement of the final accuracy of the classification.
