Physics-informed GANs for Coastal Flood Visualization
This work provides improved, intuitive flood visualizations for emergency managers to enhance mission planning during hurricanes, addressing a critical need for better adaptation tools in the face of increasing natural disaster intensity.
The paper developed a deep learning pipeline using a physics-informed GAN (pix2pixHD) to generate photorealistic satellite images of current and future coastal flooding. This model was trained to be physically consistent with NOAA SLOSH storm surge model outputs and outperformed baseline models in both physical consistency and photorealism when evaluated against physics-based flood maps.
As climate change increases the intensity of natural disasters, society needs better tools for adaptation. Floods, for example, are the most frequent natural disaster, but during hurricanes the area is largely covered by clouds and emergency managers must rely on nonintuitive flood visualizations for mission planning. To assist these emergency managers, we have created a deep learning pipeline that generates visual satellite images of current and future coastal flooding. We advanced a state-of-the-art GAN called pix2pixHD, such that it produces imagery that is physically-consistent with the output of an expert-validated storm surge model (NOAA SLOSH). By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism. While this work focused on the visualization of coastal floods, we envision the creation of a global visualization of how climate change will shape our earth.