Landslide Risk Zoning using Logistic Regression and Anfis Models in Hashtjin Catchment Area in Ardabil Province

Landslides are one of the most important environmental processes, especially in mountainous landscapes. Identifying sensitive areas and preparing a landslide risk zoning map is an important step in preventing and reducing the damage caused by this phenomenon. Hashtjin basin, with its mountainous face and considering the geological, lithological, climatic and human conditions, has the necessary conditions for the formation of landslides; therefore, the current study aims at landslide risk zoning in the given area. Therefore, landslide sensitivity analysis for Hashtjin watershed is evaluated according to the efficiency of the results obtained from two models of logistic regression and Anfis to achieve the research goal. Using the interpretation of aerial photographs and field visits, control areas, as a dependent variable, were recorded by GPS. Then, the factors affecting landslides in the area including slope, direction, elevation lines, distance from waterway, distance from fault, distance from road, geology, land use and rainfall were identified according to various sources, field studies and consultation with experts; Then, layers were prepared as independent variables in GIS Arc environment. Moreover, logistic and ANFIS regression models were implemented by entering the aforesaid layers into TERRSET and MATLAB software environment, respectively. The final landslide hazard map of the area was prepared in 5 hazard classes. In this study, 25% of the control samples were used as test data to measure the accuracy of the studied models. The results of validation of the performance of the mentioned models by performing the ROC curve showed that the accuracy of Anfis model and logistic regression were equal to 88.23 and 86.45%, respectively. The findings from Enfis model reveal that approximately 4854 hectares, equivalent to 20.6% of the Hashtjin area are in high and very high class in terms of landslide risk.