Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms

Landslides are a dangerous natural hazard that can critically harm road infrastructure in mountainous places, resulting significant damage and fatalities. The primary purpose of this study was to assess the efficacy three machine learning algorithms (MLAs) for landslide susceptibility mapping including random forest (RF), decision tree (DT), support vector (SVM). We selected case region is frequently affected by landslides, important Kamyaran–Sarvabad Kurdistan province Iran. Altogether, 14 evaluation factors were input into MLAs slope, aspect, elevation, river density, distance river, fault, fault road, land use, slope curvature, lithology, stream power index (SPI), topographic wetness (TWI). identified 64 locations landslides field survey which 70% randomly employed building training while remaining used validation. area under receiver operating characteristics (AUC) reached value 0.94 compared 0.82 forest, 0.75 machines model. Thus, model most accurate identifying areas at risk future landslides. obtained results may inform geoscientists those decision-making roles management.