Machine learning and SHAP-based susceptibility assessment of storm flood in rapidly urbanizing areas: a case study of Shenzhen, China

In recent years, urban flooding disasters have occurred frequently. Conducting research on flood susceptibility assessment is critical for urban flood prevention and urban renewal planning. However, determining how to effectively improve the accuracy of flood susceptibility assessment remains a challenging topic. Combining machine learning algorithms and SHapely Additive exPlanations (SHAP) method, this study proposes an effective technical framework for urban flood susceptibility assessment. Firstly, in terms of data selection, three types of data sources were considered comprehensively. Then, based on the above data sources, five different experimental scenarios were constructed and feature preferences were performed using SHAP. Finally, the performance differences of five commonly used advanced machine learning algorithms are compared. The results show that it is feasible to use the feature importance information provided by SHAP for feature optimization. Compared with the experimental scenario without feature optimization, feature optimization greatly improves the performance of the model. XGboost works best when paired with the optimal feature combination, and its AUC value reaches the maximum. The results indicate that in urban flood susceptibility assessment studies, the selection of the optimal machine learning algorithm and the best combination of features are important to improve the accuracy and reliability of the assessment.