nirchai

The purpose of this research is to evaluate the amount of soil loss in the land uses of the Nirchai watershed using the RUSLE model in Ardabil province. In order to carry out this research, first, the satellite image of the studied area related to the year 1400 and the month of June was received from the American Geological Research Center, and after atmospheric and radiometric corrections, a land use map was prepared using the supervised classification method using the support vector machine method. Then the RUSLE model was used to estimate the erosion rate. SPSS 21, Excel, ArcGIS 5.4, Archydro and ENVI 5.3 software were used to analyze and produce maps in this research. RUSLE model parameter layer includes rain erosion layer, soil layer, topography layer, vegetation layer and soil protection factor as well as various statistics related to rain gauge stations, hydrometry, topographic maps 1:50000, geology 1:100000 as well as DEM (20 meters area) and GIS geographic information system and remote sensing have been used. The results of this study showed that the average amount of annual soil erosion for the whole basin ranges from 0.5 to 14.25 tons per hectare per year. Also, the investigation of the regression relationships between the factors of RUSLE model and the amount of annual soil erosion showed that the topography factor (LS) with the highest value of the coefficient of determination R^2=0.93 is the most important in estimating the annual soil erosion using the RUSLE model.

Land use classification has always been one of the most important applications of remote sensing, and for this reason, different methods have been developed. With the passage of time, more advanced methods with higher accuracy were created, which increased the accuracy and performed better in extracting classes that were spectrally closer to each other. Algorithms for detecting changes in remote sensing images are divided into two categories: pixel-based and object-oriented, based on the minimum processing unit. The purpose of this research is to evaluate and prepare a land use map of the Nirchai watershed in Ardabil province using the object-oriented method. Land use classification including segmentation of image data was done using multi-scale segmentation algorithm in eCognition software environment. Then these parts were selected and classified and evaluated using the object-oriented nearest neighbor algorithm. The results showed that the object-oriented classification has an overall accuracy of 99 and a kappa coefficient of 0.88%, which indicates the high accuracy of the object-oriented method in classification. Also, the land use map showed that the use of water areas and poor pastures occupied the least (70 hectares) and the most (8069 hectares), respectively.