An innovative,fast method for landslide susceptibility mapping using GIS-based LSAT toolbox

摘要

In this study, landslide susceptibility maps (LSM) of the Akincilar region were produced with the methods of frequency ratio (FR), information value (IV), logistic regression (LR), random forest (RF), and multi-layer perceptron (MLP) by using a new GIS-based toolbox (LSAT, Landslide Susceptibility Assessment Tool). LSAT was used to assess the landslide susceptibility of the Akincilar region located 150 km northwest of Sivas city (Turkey). LSM was successfully constructed using five different methods for the study area. Area under the curve (AUC) values were calculated as 70.95%, 71.85%, 72.57%, 72.67%, 73.93% for prediction rate of FR, IV, LR, MLP and RF methods, respectively. Time-consuming processes are one of the significant problems of constructing LSM. LSAT can be used easily in this type of study and minimizes such problems. Data preparation processes, visualization of modeling results, and accuracy assessment of LSM could very quickly and automatically be done thanks to this tool.