Spatial landslide susceptibility mapping using integrating an adaptive neuro-fuzzy inference system (ANFIS) with two multi-criteria decision-making approaches

Landslide is a type of slope process causing plethora economic damage and loss lives worldwide every year. This study aimed to analyze spatial landslide susceptibility mapping in the Khalkhal-Tarom Basin by integrating an adaptive neuro-fuzzy inference system (ANFIS) with two multi-criteria decision-making approaches, i.e., best-worst method (BWM) stepwise weight assessment ratio analysis (SWARA) techniques. For this purpose, first step was prepare inventory map, which then divided randomly into 70/30% for model training validation. Thirteen conditioning factors were selected based on previous studies available data. In next step, BWM SWARA methods utilized determine relationships between sub-criteria landslides. Finally, maps generated implementing ANFIS-BWM ANFIS-SWARA ensemble models, several quantitative indices such as positive predictive value, negative sensitivity, specificity, accuracy, root-mean-square-error, ROC curve employed appraise accuracy each model. The results indicated that (AUC = 75%, RMSE 0.443) has better performance than 73.6%, 0.477). At same time, had maximum values 87.1%, 54.3%, 40.7%, respectively. As result, more efficient ANFIS. Evidently, (LSMs) can be very managing land use preventing caused phenomenon.