14. Case Study 6: Urban Flood Susceptibility Modelling of Srinagar Using Novel Fuzzy Multi-layer Perceptron Neural Network

Urban flooding (often referred to as water logging) is defined as the submergence of normally dry city areas by a considerable volume of water caused by heavy precipitation or overflowing of water bodies. Flood susceptibility modelling, by combining the effects of natural and human factors, determines the sensitivity of the space to flood hazard. Urban flood modelling has gained attention recently and since the incidence of urban floods has increased rapidly, due attention needs to be given to the urban flood studies. In this case study, urban flood susceptibility modelling of Srinagar City, Jammu and Kashmir, India, using Fuzzy MLPNN, has been carried out in Geographic Information System (GIS) environment. Fuzzy MLPNN is a simple and straightforward approach that unifies the complexity of the phenomenon of urban flooding by integrating fuzzy mathematics and machine learning to build a predictive model for the analysis of urban flood susceptibility using geospatial data. Eight flood conditioning factors (elevation, slope, profile curvature, plan curvature, geology, distance from natural streams, MFI and LULC) were used as independent variables along with urban flood locations as the dependent variable. A precursory FSZ map of Srinagar City was created using the frequency ratio technique, and non-flooded locations were accordingly determined. The developed model reveals the susceptibility of each and every pixel (12.5 × 12.5 m area) in the study area. The FSI, illustrated by the FSZ Map of Srinagar, demonstrates considerable susceptibility of the city to urban flood hazard. The dominant influence of spatiality of precipitation and water bodies is indicated by the conclusion that highly susceptible regions of the city are those where MFI is high and proximity to natural drainage is low. The FSZ map was validated using Area under the ROC Curve (AUC) Analysis, which substantiates the efficiency of the Fuzzy MLPNN model. With 0.931 and 0.922 AUC values, the success rate and predictive performance of the FSZ map come out to be excellent, respectively.