Based on the statistical data of waterlogging points in Shenzhen City from 2018 to 2022, the spatiotemporal distribution characteristics of waterlogging points in Shenzhen City were analyzed using methods such as standard deviation ellipse, spatial autocorrelation, and kernel density estimation. Using the optimized hotspot analysis and kernel density estimation to obtain the susceptibility to waterlogging as the dependent variable, respectively, the optimal parameter geographic detector was used to discretize the continuous driving factors and explore the main driving factors and the mechanisms of spatial distribution differences in waterlogging points. The results show that there are significant differences in the spatial distribution of waterlogging points in Shenzhen City, with weakened directionality and obvious clustering characteristics. The population economic driving factors have the strongest explanatory power for the spatial distribution of waterlogging points, followed by the climate characteristics. The synergistic effect of rainstorm days and population driving factors can explain 59.50% of the distribution of waterlogging points. The susceptibility obtained from kernel density estimation has better representativeness, and the optimal discretization of continuous factors can significantly improve their explanatory power. Keywords: urban waterlogging; waterlogging points; optimized hot spot analysis; kernel density estimation; optimal parameter-based geographical detector; Shenzhen City 〖FL