An integrated GPU-accelerated modeling framework for high-resolution simulations of rural and urban flash floods

This paper presents an integrated modeling framework aiming at accurate predictions of flood hazard from heavy rainfalls. The accuracy of such predictions generally depends on the complexity and resolution of the employed model components. We propose an integration of complementary models in one framework that facilitates GPUs to improve accuracy and simulation time. The spatially distributed runoff model integrates surface flow routing based on the full shallow water equations, infiltration based on the Green-Ampt equation, and interception. In urban areas, the runoff model is coupled with the Storm Water Management Model (SWMM). The integrated model is validated and tested on laboratory, rural and urban scenarios with regards to accuracy and computational efficiency. The GPU acceleration yields speedups of 1000 times compared to a CPU implementation and enables the coupled simulation of flash floods at 1 m resolution for an urban area of 200 km(2) in realtime.