Investigating and Monitoring Land Use Changes Using Geographic Information System, Remote Sensing Technique and Supervised Classification Methods (Case Study: Swadkoh City)

Investigation and analysis of land use changes was done using remote sensing and GIS techniques with supervised classification methods. The selected images from the years ۲۰۰۰ and ۲۰۲۲ were taken by the Landsat satellite. Necessary pre-processing of the images was done and then the best band combination was selected. The best band combinations of ۲۰۰۰ and ۲۰۲۲ were selected as ۲۴۵ and ۴۶۷, respectively, using the OIF index. The area changes from ۲۰۰۰ to ۲۰۲۲, in the support vector machine method, the uses of dense pasture, poor pasture, agriculture, residential, forest have had area changes of ۹۵۸۰.۵۳, ۳۴۲۶۷.۴۹, ۲۳۷.۲, ۱۶۰۳.۴۱, ۲۶۵۲۷.۵۷ hectares. Therefore, the use of dense pasture and forest has decreased by ۵.۸۷% and ۱۶.۲۵%, and other uses have increased. The area changes from ۲۰۰۰ to ۲۰۲۲, in the neural network method, the uses of dense pasture, poor pasture, agriculture, residential, forest have had area changes of ۶۰۲۱.۰۵, ۳۳۸۶۹.۵۷, ۳۶۰.۷۹, ۱۴۹۲.۱۶, ۲۹۷۰۱.۴۷ hectares. Therefore, the use of dense pasture and forest has decreased by ۳.۶۹% and ۱۸.۲۰%, and the use of poor pasture has increased by ۲۰.۷۵%, agriculture by ۰.۲۲%, and residential by ۰.۹۱%. In the assessment of classification accuracy, kappa coefficient and overall accuracy in the support vector machine method in ۲۰۰۰ were ۰.۸۴ and ۰.۸۷ and in ۲۰۲۲, ۰.۸۶ and ۰.۸۸ were obtained. Kappa coefficient and overall accuracy were obtained in ۲۰۰۰, ۰.۹۴ and ۰.۹۵ and in ۲۰۲۲, ۰.۹۶ and ۰.۹۷ in the neural network method. Therefore, the neural network method has higher accuracy.

کلیدواژه ها:

land use ، Kalardasht city ، remote sensing ، Neural network