Zoning of landslide-prone areas using neuro-fuzzy inference system (ANFIS) (Case Study: Songhurchay River Basin)

In this study, Neural Fuzzy Inference System (ANFIS) was used in landslide zoning in the Songhur Chai River Basin. In order to assess the neural network, 124 occurred landslide data identified from aerial photographs, satellite imagery, and field observations and was presented to the system. In addition, for processing landslides in MATLAB software, 8-layers were prepared; slope layers, aspect, DEM, lithology, hydrographic network layer, NDVI, soil and landslide groups and landslide distribution were drawn from field studies, topographic and geologic maps and satellite images in Arc GIS software. These layers were normalized based on the largest value for each layer in the range between 1 and zero. During the modeling process, 80% of the data were selected for training and 20% for were tested and were processed in the neural fuzzy inference system. In several studies, the value is considered acceptable. Then, the values in order to map the landslide in the structure of ANFIS were processed and analyzed. Finally, with respect to the output weights, landslide zonation maps were drawn into five categories: very high, high, medium, low and very few. The results indicated that the geological structure formed of gray man and red sandstone, volcanic ash and tuff and high humidity, makes Ganjgah Mountains and Islamabad a high potential area for landslide occurrence