A landslide susceptibility area mapping using bivariate statistical models Frequency ratio (FR) and Shannon entropy (SE) was conducted using the Geographic Information Systems (GIS) platform in Kulawi District in Indonesia. Landslides often occur with high intensity in Kulawi District and cause road and bridge access to be cut off. There were 718 landslides identified covering a total area of 2.10 km2. Twelve landslide conditioning factors such as elevation, slope, curvature, aspect, topographic wetness index, lithology, distance from fault, distance from road, distance from river, land cover, normalized difference vegetation index, and precipitation were integrated with past landslide event data to determine the weight of each landslide conditioning factor and factor class using FR and SE models. In the solution process, landslide event data were grouped into training data and testing data. The area under the curve (AUC) of the receiver operating characteristic was used to evaluate the model performance. The results of this study indicated that the FR and SE models each produced the accuracy of 74.86% and 72.25%, while the prediction rate was 73.65% and 72.78%, respectively. The landslide susceptibility map represents the predicted landslide area, therefore the results of this study can be used to reduce the potential for landslide-related hazards in the study area.
Aldiansyah et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: