Urban flood susceptibility prediction using a Fuzzy-Delphi hybrid model in Sanandaj City

Introduction
Although a flood is an extreme and exceptional flow, every exceptional flow will not turn into a destructive flood, different factors must be changed in nature to cause destruction, damage, and casualties. In general, floods can be divided into four groups flash floods, river floods, urban floods, and coastal floods. Urban floods usually cause fewer casualties and mainly create damage caused by flooding, disruption of traffic, interruption in socio-economic activities, and problems of this kind. The damage caused by non-urban floods is often heavy and sometimes accompanied by high and catastrophic casualties. According to the Mediterranean climate, Iran is the seventh country in the world in terms of flooding. The flood-prone areas of the country are estimated to be around 91 MHA. In other words, 55% of the country's surface has contributed to the production of surface runoff, of which about 42 MHA have moderate to very high flood intensity. The review of sources shows the development of knowledge-based methods, statistical methods, and artificial intelligence algorithms in predicting flood-prone areas in urban and non-urban watersheds in different regions worldwide. However, a hybrid method of the Fuzzy, Delphi, and Analytic Hierarchy Processes (FDAHP) in urban flood susceptibility has not been used. Regarding the questions, what are the most important factors in urban flood occurrence? Is it possible to determine flood-prone areas in urban areas using the FDAHP hybrid model?, this study aims to identify the factors influencing the occurrence of floods and predict flood-prone areas in Sanandaj City.
 
Materials and Methods  
In this study, which has a descriptive-analytical-comparative approach, to predict floods in Sanandaj City, the FDAHP was used. First, each of the conditioning factors (14 factors) was scored by flood experts and completed using the scores obtained from other stages of the FDAHP model. After collecting the opinions, the relative weights of the indicators were determined using the hybrid model, and finally, the flood susceptibility map of Sanandaj City was prepared using ArcGIS 10.5 software. The different stages of modeling with the FDAHP method are as follows: 1) experts' opinions, First, with the help of experts (technical and executive experts of the Kurdistan Province and Sanandaj Municipality's Natural Resources and Watershed Administration) the decision-making parameters according to their importance qualitatively or, if possible, quantitatively they rate. (Opinion scales are: very important with a nine score, importance with a seven score, average importance with a five score, low importance with a three score, and no importance with a one score). 2) Calculation of fuzzy numbers. After the preliminary stage, which includes a survey of experts in the form of a qualitative or quantitative questionnaire, fuzzy numbers were calculated based on the results of this survey. 3) Forming the matrix of fuzzy pairwise comparisons. 4) Calculating the fuzzy weight of the parameters. 5) De-fuzzification of model parameters. 6) Evaluation of the accuracy of the output of the spatial flood prediction model.
 
Results and Discussion
The findings showed that slopes of less than 10% (flat), areas with an elevation of fewer than 1400 m above sea level, slope aspect and curvature (flat), urban land use with high building density, rainfall of more than 369 mm and rock type Qt2 (Quaternary alluvium) have the highest susceptibility to floods compared to other types in Sanandaj City. Also, the results show that, on the one hand, increasing the distance from the residential areas, the distance from the roads, and the distance from the waterways decreases the susceptibility to urban flooding. On the other hand, with the increase in building density, the density of roads and the density of waterways in Sanandaj increases the susceptibility to flooding. These results are consistent with the other studies that concluded the residential areas with the largest area have the highest risk of vulnerability. Our findings indicated that the density of the waterway, the slope, and the distance from the waterway have the most influence on the occurrence of floods in Sanandaj City. Rainfall, road density, building density, distance from residential areas, distance from roads, flow accumulation, elevation, land use, lithology, and slope curvature are the next priorities in terms of importance in the occurrence of floods in Sanandaj City.
 
Conclusion
The flood prediction map showed that a large part of Sanandaj City including the City's northern, western, southern, and center, which is crowded, has more potential for urban flooding. For example, the old and dilapidated buildings of the City center are highly susceptible to floods, but the border areas around the City have less exposure to this phenomenon. Therefore, as the distance from the City center and the residential regions increases, the potential for flooding decreases. Based on the value of 80.56% of the area under the curve, the validation results indicated that 80.56% of the areas where urban flooding is visible have been correctly predicted. The FDAHP hybrid model had a high ability to estimate the areas prone to urban flooding and, therefore it can be tested and evaluated as a management tool to identify urban floods in other similar areas. Since our aim concerning the occurrence of floods is more on flood mitigation, according to the mentioned theoretical bases and the existing views in the field of flood prediction maps, it can be stated that the ruined canals and the network of waterways, unauthorized constructions, high density, and elevation of buildings, old and dilapidated buildings and the irregularity of the canals have aggravated the urban flooding. Overall, it can be said that obtaining an accurate and reasonable urban flood prediction map can help City managers and planners identify flood-prone areas to manage the urban flood crisis.