Sandwiched Lo-res Simulation for Scalable Flood Modeling

High-resolution flood modeling is enabled by utilizing high-resolution input derived by remote sensing technologies such as Light Detection and Ranging (LiDAR) systems. However, there is a long-standing trade-off between the computational time and spatial resolution for a flood simulation. In this paper, we propose a novel deep learning-based geospatial encoder-decoder for flood modeling consisting of (i) accuracy-preserving coarse-graining of the input, (ii) simulating flood on the coarser input, and (iii) downscaling the simulated flood to super-resolution. Our experiments show that our approach accelerates flood modeling up to 50 times faster with 1/16 scale while MSE of 0.0179, which is 10.3% less than the baseline with bilinear interpolation. Especially, we observe 20.5% reduction of MSE on average for the 5% worst cases.