LAUSR

The public health risk caused by urban floods is a global concern. Flood risks are amplified by the interaction of rainfall and storm tides in coastal cities. In this study, we investigate the flood risks of rainfall and storm tides coupling statistical and hydrodynamic models and evaluate the influence of different parameter estimation methods and bivariate return periods (RPs) on flood risks in the coastal city. The statistical model is used to obtain the bivariate design of rainfall and storm tides with the integration of copula function, most-likely weight function and Monte Carlo simulation method. The bivariate designs are adopted as the input boundaries for the hydrodynamic model established by Personal Computer Storm Water Management Model (PCSWMM), and the flood risk is evaluated by the hydrodynamic model. Subsequently, the influence of different parameter estimation approaches (that is, parametric and non-parametric) and bivariate RPs (that is, co-occurrence RP, joint RP, and Kendall RP) on bivariate designs and flood risks are investigated. With Haikou coastal city in China as the case study, the results show that: (1) Gumbel copula is the best function to describe the correlation structure between rainfall and storm tides for the parametric and non-parametric approaches, and the non-parametric approach is a better fit for the observed data; (2) when the Kendall RP is large (more than 100 years), the flood risk is underestimated with an average of 17% by the non-parametric estimation, and the parametric estimation approach is recommended as it is considered the most unfavorable scenario; (3) the types of bivariate RP have the important impact on the flood risk. When there is no specific application need, the Kendall RP can be adopted as the bivariate design standard of flooding facilities since it can describe the dangerous areas more accurately for multivariate scenario. The results can provide references for reasonable flood risk assessment and flooding facility design in coastal cities.