Landslide susceptibility mapping at Golestan Province, Iran: A comparison between frequency ratio, Dempster–Shafer, and weights-of-evidence models

The purpose of the present study is to investigate the landslide susceptibility mapping using three statistical models such as frequency ratio, Dempster–Shafer, and weights-of-evidence at southern part of Golestan province. At first, landslide locations were identified from the interpretation of aerial photographs, and field surveys. A total of 392 landslides were mapped in GIS out of which 275 (70%) locations were chosen for the modeling purpose and the remaining 118 (30%) cases were used for the model validation. Then layers of the landslide conditioning factors were prepared. The relationship between the conditioning factors and the landslides were calculated using three models. For verification, the results were compared with landslides which were not used during the training of the models. Subsequently, the ROC (Receiver operating characteristic) curves and area under the curves (AUC) for three landslide susceptibility maps were constructed and the areas under curves were assessed for validation purpose. The validation results showed that the area under the curve for frequency ratio, Dempster–Shafer, and weights-of-evidence models are 0.8013 (80.13%), 0.7832 (78.32%), and 0.7460 (74.60%) with prediction accuracy 0.7516 (75%), 0.7396 (73%), and 0.6998 (69%) respectively. The results revealed that frequency ratio model has higher AUC than the other models. In general, all the three models produced reasonable accuracy. The resultant maps would be useful for general land use planning.

► We used three models i.e. frequency ratio, Dempster–Shafer (DS) and weights-of-evidence models (WoE). ► We find that all three models have good predictive capacity and efficient in landslide susceptibility mapping. ► Among all models, frequency ratio method performed slightly better than the other two.