Data acquisition and analysis for land slide susceptibility mapping using Geographical Information System (GIS) at Nilgiris district, India

The purpose of this study is to develop technique for landslide susceptibility mapping using. artificial neural networks and then to apply the technique to the selected study area at Nilgiris district in Tamil Nadu. Landslide locations are identified by interpreting the satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use. Then the landslide-related factors are extracted from the spatial database. These factors are then used with an artificial neural network to analyze landslide susceptibility. Each factor's weight is determined by the back-propagation training method. Different training sets will be identified and applied to analyze and verify the effect of training. The landslide susceptibility index will be calculated by back propagation method and the susceptibility map will be created with a GIS program. The results of the landslide susceptibility analysis are verified using landslide location data. In this research GIS is used to analysis the vast amount of data very efficiently and an ANN to be an effective tool to maintain precision and accuracy. Finally the artificial neural network will prove it's an effective tool for analyzing landslide susceptibility.