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 physicalconsistency 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 10 . Flood map GAN Pre-flood sat. img. Post-flood satellite imageFigure 1: We have generated the first physically-consistent satellite imagery of coastal flood events (mid). During hurricanes, such as Harvey in Houston, TX, the area is largely covered by clouds and emergency responders must rely on nonintuitive flood maps, inferred from models or radar, for mission planning (bottomright, [1]). We propose a novel GAN-based pipeline to convert the flood maps into photorealistic post-flood images, enabling emergency managers to intuitively understand flood impacts.

As climate change increases the intensity of natural disasters, society needs better tools for adaptation. Floods, for example, are the most frequent natural disaster, and better tools for flood risk communication could increase the support for flood-resilient infrastructure development. Our work aims to enable more visual communication of large-scale climate impacts via visualizing the output of coastal flood models as satellite imagery. We propose the first deep learning pipeline to ensure physical-consistency in synthetic visual satellite imagery. 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. We envision our work to be the first step towards a global visualization of how climate change shapes our landscape. Continuing on this path, we show that the proposed pipeline generalizes to visualize arctic sea ice melt. We also publish a dataset of over 25k labelled image-pairs to study image-to-image translation in Earth observation 1 .

No abstract