Quantitative Assessment of Affected Population Risk by Tropical Cyclones Using the Hybrid Modeling Combining GAM and XGBoost: A Case Study of Hainan Province

Abstract

Global climate change is expected to increase the proportion of intense tropical cyclones in the Northwest Pacific. This study focuses on how factors, especially extreme events, may affect disaster losses. To address this issue, an event-based multivariate tropical cyclone risk assessment model, which employs Copula, generalized additive model, and undersampling extreme gradient boosting decision tree techniques, is developed to enhance the accuracy of disaster loss prediction. The results suggest that on Hainan Island, the rate of the affected population is positively correlated with maximum wind speed and maximum daily rainfall but negatively correlated with gross domestic product and elevation. The study also shows that the tropical cyclone risk in the cities in Hainan increases as the return periods expand, and each return period scenario shows a unique geospatial distribution of the tropical cyclone risk on Hainan Island, with higher risks in coastal and eastern regions. These results emphasize the importance of implementing effective disaster management strategies to mitigate the impact of severe tropical cyclones in the region.