A number of approaches have been used inlandslide susceptibility mappingand there seems to be no agreement on which approach provides best prediction of landslide susceptibility. This study was conducted to develop landslide susceptibility mapsof the Tinalah watershed at a 1:25000 scale using analytical hierarchy process (AHP), statistical index (SI), index of entropy (IOE) and logistic regression (LR) approaches and to compare performance of those approaches in predicting landslide susceptibility. Out of 114 landslides identified during site investigation, 86 landslides were selected for landslide susceptibility analyses, while the remaining 28 landslides were used to verify the results. Factors controlling landslides considered in the landslide susceptibility mapping were slope inclination, lithology, distance to fault, land use, distance to river, and rainfall. Analyses of Receiver Operating Characteristics (ROC) curves showed that the AUC values of the landslide susceptibility maps derived using AHP, SI, IOE and LR approaches were 0.784, 0.688, 0.827 and 0.834, respectively. The LR approach was concluded to perform the best in predicting landslide susceptibility in the study area.
A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping
