Evaluation of Shannon Entropy and Weights of Evidence Models in Landslide Susceptibility Mapping for the Pithoragarh District of Uttarakhand State, India

Landslide susceptibility mapping is considered a useful tool for planning, disaster management, and natural hazard mitigation of region. Although there are different methods predicting landslide susceptibility, the bivariate statistical analysis method to be simple popular. In this study, main aim evaluate performance Shannon entropy (SE) weights evidence (WOE) models in Pithoragarh district Uttarakhand state, India. For purpose, ten affecting factors, namely, slope degree, aspect, curvature, elevation, land cover, forming materials, geomorphology (landforms), distance rivers, roads, overburden depth were used development maps using SE WOE methods. Data extracted from Google Earth images, Aster Digital Elevation Model, Geological Survey India report construction evaluation maps. The data 91 locations randomly divided into two parts ratio 70 : 30 GIS software that 70% was training 30% testing validating models. Performance applied evaluated area under AUC (area curve) ROC (receiver operating characteristics) curve. Results indicated model having better accuracy (AUCWOE = 68.75%) than (AUCSE 52.17%) Hence, can accurate which provide information decision maker policy planner prone areas.