Investigating optimal 2D hydrodynamic modeling of a recent flash flood in a steep Norwegian river using high-performance computing

Abstract

Efficient flood risk assessment and communication are essential for responding to increasingly recurrent flash floods. However, access to high-end data center computing is limited for stakeholders. This study evaluates the accuracy-speed trade-off of a hydraulic model by (i) assessing the potential acceleration of high-performance computing in PCs versus server-CPUs and GPUs, (ii) examining computing time evaluation and prediction indicators, and (iii) identifying variables controlling the computing time and their impact on the 2D hydrodynamic models' accuracy using an actual flash flood event as a benchmark. GPU-computing is found to be 130× and 55× faster than standard and parallelized CPU-computing, respectively, saving up to 99.5% of the computing time. The model's number of elements had the most significant impact, with <150,000 cells showing the best accuracy-speed trade-off. Using a PC equipped with a GPU enables almost real-time hydrodynamic information, democratizing flood data and facilitating interactive flood risk analysis.