Integration of GIS and artificial neural networks to map the landslide susceptibility in Nilgiris district

Abstract

The term landslide includes a wide range of ground movement, such as slides, falls, flows etc. mainly based on gravity with the aid of many conditioning and triggering factors. Particularly in the last two decades, there is an increasing international interest on the landslide susceptibility, hazard or risk assessments. In Tamil Nadu state, Landslides are very severe in the Nilgiris district. The major landslides in the Nilgiris hills are the Runnymede landslide, the Glenmore slide, the Coonoor slide and the Karadipallam slide. The purpose of this research is to device a new methodology to map the landslide susceptibility with the help of Artificial Neural Networks and Analytical Hierarchical Process using a unified platform of Remote Sensing, Geographical Information System and socio economic survey data. The socio economic impact is analyzed using the data collected from census department of Tamil Nadu government and field survey. This technique is applied in Nilgiris district in Tamil Nadu and the socio economic impact of the landslide is analyzed. Landslide locations are identified by interpreting remote sensing satellite images, field survey data, and a spatial database of the topography. The landslide susceptibility index is calculated by back propagation network (BPN) and the susceptibility map is created with a GIS program. The results of the landslide susceptibility analysis are verified using previous landslide location data and tested with 26 test cases. Thus, keeping in mind, the requirements of hazard planners and decision makers need for Landslide Hazard Zonation map has been systematically prepared. In this research GIS is used to analyze the vast amount of geospatial data efficiently. An ANN is an effective tool to maintain precision and accuracy in mapping the landslide susceptibility.