“…Conventionally, hydrodynamic models have been employed for applications such as flood inundation simulations, the assessment of mitigation, and adaptation measures (Wolfs and Willems, 2013;Wang et al, 2021;Li et al, 2019). Despite the fact that the physically based models can simulate the drainage and surface flooding processes well, they usually require a large number of inputs to describe the model structure and parameters and are often computationally intensive, especially with the adoption of two-dimensional calculations (Yin et al, 2020;Jamali et al, 2018;Ziliani et al, 2019;Hou et al, 2021b). Meanwhile, there is an inevitable need for conceptualization and simplification in the physical model, and the relevant calibration and validation procedures are also quite challenging (Davidsen et al, 2017;Coulthard et al, 2013;Wu et al, 2018).…”