Multivariate statistical algorithms for landslide susceptibility assessment in Kailash Sacred landscape, Western Himalaya

Landslide susceptibility mapping plays an imperative role in mitigating hazards and determining the future direction of developmental activities mountainous regions. Here, we used 518 landslide occurrences nine landslide-conditioning parameters to build vulnerability models Kailash Sacred Landscape (KSL), India. Four multivariate statistical were applied, namely generalized linear model (GLM), maximum entropy (MaxEnt), Mahalanobis D2 (MD), support vector machine (SVM), calibrate compare four maps susceptibility. The results demonstrated outperformance for predictability compared other obtained from area under receiver operating characteristic curve (ROC). ensemble data shows that 10.5% landscape has susceptible conditions landslides, whereas 89.50% falls safe zone. occurrence landslides KSL is linked middle elevations, vicinity water bodies, motorable roads. Furthermore, observed patterns resulting exhibit major variables cause their respective significance. current modelling approach could provide baseline at regional scale improve planning KSL.