عنوان مقاله [English]
The flood is the second natural disaster that causes damage to human societies every year. In the meantime, cities and population centers have the most risk and potential for physical damage caused by flood events. Therefore, the purpose of this study was to predict the risk of flood in Sanandaj City in Kurdistan province, using hybrid models in the GIS environment. Factors influencing the flood occurrence in this study were inclination, slope, elevation, distance from the river, river density, flow accumulation, land use, gradient curvature, lithology, and distance from the passage, road density, and distance from the building, Build density and rainfall. After collecting the required data and layers, we use the two algorithms, including definitive statistical index (SI) and evidential belief function (EBF) in both individually and in combination. The predicted location of the flood susceptibility was developed in Sanandaj City. In order to evaluate the performance of the model, the AUC curve obtained from the ROC curve was used. According to the assessment criteria used in this study (ROC) and according to the validation data, the model of EBF (0.840) in comparison with SI (0.827) model had the best function in flood hazard mapping in the study area. The accuracy rate of hybrid model of SI-EBF based on the ROC result was equal to 0.849 that it is showed that the performance of the SI-EBF hybrid model in predicting the spatial hazard of floods in the present study yielded better results than the individual models. Finally, results of this study showed that Sanandaj flood spurts are due to various environmental and human factors that can be provided based on flood hazard map and appropriate management measures to reduce damages and flood damage.