Abstract:

In order to clarify the relationship between precipitation events and insurance claims and enhance meteorological insurance services, this study utilized 703 insurance claim records and hourly precipitation data from Hunan province (2021−2024). A random forest model was used to construct thresholds for precipitation insurance claims in county−level urban areas in Hunan province, followed by a significance test. The results showed that: （1） the random forest model outperformed XGBoost and LightGBM in precision, Critical success index (CSI) and accuracy, demonstrating superior simulation of insurance claim thresholds. It effectively evaluated the thresholds across different locations and time windows. （2）Cumulative precipitation 120h, 96h and 72h prior to claims, along with the maximum hourly precipitation whthin 120h, showed high feature importance scores, identifying them as key claim−influencing factors. （3）Significant spatial heterogeneity existed in precipitation claim thresholds. The conclusion that 'higher precipitation intensity let to a higher likelihood of claims' did not hold spatially. Low−threshold regions (cumulative 120h precipitation <50mm) accounted for 40% of claimed areas, indicating high sensitivity to precipitation events and vulnerability to disasters. High−threshold regions (cumulative 96h precipitation >65mm) constituted 16%, suggesting claims occur only under intense precipitation. （4）The Chi−square tests confirmed statistically significant relationships between the precipitation insurance claim thresholds of 6 prefecture−level urban areas and 19 county−level cities (districts) level urban areas constructed based on random forests, effective discrimination of claim triggers across precipitation intensities. The research results reveal an inherent correlation between the spatiotemporal distribution of precipitation and insurance claims, which can provide a scientific basis for insurance meteorological warnings and disaster prevention and reduction in Hunan province. 

Key words: Machine learning, Precipitation, Insurance, Threshold, Hunan province