Assessment the Gully Erosion Risk in Quyjoq watershed

Abstract

Prediction of occurrence of gully erosion through the use of models and output them to the hazard mapping of gully erosion, most appropriate strategy for land management planning in watersheds prevent the occurrence of erosion. in this research, the zoning of gully erosion in the Quyjoq watershed Golestan province of Multilayer Perception neural network structure and the use of variables the selected suitable factors are: slope, aspect, elevation, land unit, land use, distance to river, lithology, distance to road. SPSS modeler software and MLP method were used to perform the neural network. The method of using layers in MLP method was 1-8-9. It includes 9 input layers, 8 hidden layers and 1 output or target layer. Results of the study show that 20, 30, 24, 16 and 10 percent of the region form the areas with very high, high, medium, low and very low risk of erosion. This finding is primarily related to streams, roads and geology. The produced gully erosion susceptibility maps can be helpful to make decisions for soil and water planning and management and finally sustainable development in the Quyjoq watershed.

Keywords

• golestan
• gully erosion
• loess
• artificial neural network