Flood vulnerability mapping and urban sprawl suitability using FR, LR, and SVM models, Taif area, KSA

Abstract Flooding is a natural but inevitable phenomenon that occurs over time. It not only damages human lives, property, and resources but also slows down the economy of a country. In this study, an attempt was made to establish suitability map for future urban development based on flood vulnerability maps in Taif catchment area, Saudi Arabia. For this purpose, three models including, bivariate (FR), multivariate (LR), and machine learning (SVM) were used. Thirteen parameters were used as flood-contributing parameters. The inventory map was created using field surveys, historical data, analysis of RADAR (Sentinel-1A), and Google Earth images collected between 2013 and 2020. Generally, 70% flood locations were randomly selected from the flood inventory map to generate the flood susceptibility model, and the remaining 30% flood points were used to model validation. The flood susceptibility map was classified into five zones: very low, low, moderate, high, and very high. The AUC value used to predict the performance of the models, showed that the accuracy reached 89.5, 92.0, and 96.2% for the models FR, LR and SVM, respectively. Accordingly, the flood susceptibility map produced by the SVM model is accurate and was used to construct flood vulnerability map with the help of urban and road density maps. This step followed by integrating slope and elevation maps with the flood vulnerability model to produce the final suitability map that was classified into three zones, isolated zone, low suitable, and high suitable areas. Results indicated that the high suitable areas located in the east and northeast parts of the Taif Basins where flood risk is low and very low. The results of this work will improve land use planning by engineers and authorities and take possible action to reduce flood hazards in the area.