GIS-Based Approaches for the Landslide Susceptibility Prediction in Setif Region (NE Algeria)

Abstract

The present study is focused on a comparative evaluation of logistic regression (LR), frequency ratio (FR), information value (IV), and weight of evidence (WoE) methods for landslides susceptibility assessment in Bouandas region, North of Setif (NE Algeria). Information about landslide inventory and 17 pre-defined causative factors were prepared from multiple sources. The four methods are used to derive the weighted value of causative factors along the study area. The results were validated using receiver operating characteristic and the areas under the curves obtained using the FR, LR, IV and WoE methods are 0.86, 0.84, 0.81 and 0.79, respectively. The landslide susceptibility map produced from FR model is proposed to be more useful for the study area. It could reveal the relative importance of different factors in explaining landslides, and it may assist engineers in land-use planning.