Research progress and prospects of urban flooding simulation: From traditional numerical models to deep learning approaches

Abstract

The rise in urban flooding events poses a threat to public safety, property, and economic stability. To prevent urban flooding and manage stormwater effectively, relying solely on engineering solutions is insufficient. Therefore, it is critical to implement non-engineering measures such as urban flood warnings and forecasting. This article reviews the characteristics of different urban flood models based on different hydrological and hydrodynamic principles and deep learning (DL). It highlights the limitations of coupled hydrological-hydrodynamic models in terms of timeliness. Additionally, it discusses research on the use of Numerical Simulation in hydrological early warning and forecasting. Compared to traditional hydrodynamic models that rely on physical mechanisms, models driven by DL methods can effectively and adaptively extract input-output relationships of complex systems. Subsequently, a summary of the current flood models is presented, followed by a discussion of future development trends and challenges.