Flood hazard mapping in Sanandaj using combined models of statistical index and evidential belief function

The flood is the second natural disaster in terms of the damage that it causes to human societies every year. At the same time, cities and population centers are exposed to the highest risk and potential for physical damage caused by flood events. The growing trend of floods in Iran in recent years indicates that most parts of the country are at risk. According to the conducted studies, about forty large and small floods occur annually in different parts of the country. Since the flood is the most devastating disaster in the world and a serious threat to life, preparation of flood hazard maps is essential in identification of flood-sensitive areas, and is one of the first steps taken to reduce damage. It should be noted that researchers can easily identify areas with high risk using flood hazard maps to prevent damage. In the modeling of research on natural and environmental hazards such as floods, the complexity of natural systems makes it difficult to use physical models, highlighting the use of hybrid models as a suitable alternative. Therefore, it is necessary to provide appropriate methods and suggestions for estimation of runoff and flood in areas with high risk in order to prevent their occurrence. In recent years, a large number of statistical and probabilistic models have been used for flood hazard mapping, and GIS has been used as a basic analysis tool for spatial management and data manipulation due to its capability of managing large amounts of spatial data. Furthermore, it is possible using GIS prediction models to partition urban areas in terms of flood hazard. The obtained hazard maps can be used for identification of areas with high flood hazard. Today, the accuracy of flood susceptibility maps in urban areas can be increased using hybrid GIS models rather than single ones. Therefore, the purpose of this study was to predict the risk of flood in the city of Sanandaj, Kurdistan Province, Iran using hybrid models in the GIS environment. The factors considered in this study as influencing the occurrence of flood included inclination, slope, elevation, distance from the river, river density, flow accumulation, land use, gradient curvature, lithology, distance from the passage, road density, distance from the building, building density, and rainfall. After collecting the required data and layers, we used two algorithms, including the definitive statistical index (SI) and the evidential belief function (EBF), both in isolation and in combination. The locations of flood susceptibility in Sanandaj were predicted. In order to assess the performance of the model, the AUC curve obtained from the ROC curve was used. According to the adopted assessment criteria (ROC) and the validation data, the EBF model (0.840) exhibited better performance than the SI model (0.827) in flood hazard mapping in the area under investigation. The accuracy rate of the hybrid SI-EBF model was 0.849 based on the ROC results, which demonstrated that the hybrid model performed better in prediction of the spatial hazard of flood than the single models. Finally, the results of the study showed that Sanandaj flood spurts resulted from various environmental and human factors, which can be handled using flood hazard maps and appropriate management measures to reduce flood damage.