Effects of Historical Landslide distribution and DEM resolution on the Accuracy of Landslide susceptibility mapping using Artificial Neural Network

An efficient and accurate method of generating landslide susceptibility maps is very important to mitigate the loss of properties and lives caused by this type of geological hazard. The study area is Niigata, Japan sustained extensive landslide damage triggered by earthquake on 2004. This study focuses on the development of an accurate and efficient method of data integration, processing and generation of a landslide susceptibility map using an ANN (Artificial Neural Network), and data from some type of DEM (Digital Elevation Models) and landslide distribution map. DEM was generated from aerial photograph, laser scanning data, topographic map and ASTER. Two Landslide distribution maps are derived from NIED and GSI. The effects of the DEM resolution and landslide distribution on the accuracy of landslide susceptibility mapping has been analyzed using ANN in this study. The method contains two major phases. The first phase is the data integration and analysis, and the second is the artificial neural network training and mapping. The data integration and analysis phase involves GIS based statistical analysis relating landslide occurrence to geological and geomorphological parameters. The parameters include slope, aspect, elevation and geology. This phase determines the geological and geomorphological factors that are significantly correlated with landslide occurrence. The second phase further relates the landslide susceptibility index to the important geological and geomorphological parameters identified in the first phase through ANN training. The trained ANN is then used to generate a landslide susceptibility map. The area provided enough landslide data to check the efficiency and accuracy of the developed method. Based on the initial results of the experiment, the developed method is more than 90% accurate in determining the probability of landslide occurrence in a particular area.