Advancing flood damage modeling for coastal Alabama residential properties: A multivariable machine learning approach

Flooding is a global threat and predicting flood risk accurately is vital for effective mitigation and increasing society's awareness of the negative impacts of floods. Over the years, researchers have worked on physical and data-driven models to predict flood damage, striving to improve accuracy and understanding. However, the challenge lies in the scarcity and limitedness of comprehensive datasets needed to develop these models. This study aims to enhance the National Flood Insurance Program (NFIP) claims dataset from Hurricane Katrina in coastal Alabama to make it adequate for multi-variable flood damage assessment. The NFIP claims dataset was combined with the Alabama property dataset, simulated flood hazard information, and property location characteristics. Oversampling techniques are employed to address data imbalance in the datasets. Subsequently, several ensemble machine learning approaches, including random forest, extra tree, extreme gradient boosting, and categorical boosting, are utilized to develop multi-variable flood damage models. The validation of these models demonstrates that extreme gradient boosting performs best, achieving satisfactory results in identifying damaged properties with precision (0.89), recall (0.90), and F1-score (0.90), as well as determining relative damage with R-squared (0.59), root mean squared error (0.21), and Spearman correlation (0.70). Utilizing data oversampling techniques improves the model performance of imbalanced flood damage datasets. Despite the dataset's limitations and data augmentation techniques employed, the model's output explanation based on SHapley Additive exPlanations (SHAP) is constructive as it aligns with the study's expectations regarding the interaction of different features to produce the final results.