Generative modeling of spatio-temporal weather patterns with extreme event conditioning
This work addresses the need for better modeling of irregular and complex weather patterns, especially extreme events exacerbated by climate change, for researchers in geospatial data and climate science, though it is incremental as it builds on existing GAN architectures.
The paper tackles the problem of generating spatio-temporal weather patterns conditioned on extreme events, proposing a novel GAN-based approach that incorporates encoded extreme weather event segmentation masks, and demonstrates its applicability with real-world surface radiation and zonal wind data.
Deep generative models are increasingly used to gain insights in the geospatial data domain, e.g., for climate data. However, most existing approaches work with temporal snapshots or assume 1D time-series; few are able to capture spatio-temporal processes simultaneously. Beyond this, Earth-systems data often exhibit highly irregular and complex patterns, for example caused by extreme weather events. Because of climate change, these phenomena are only increasing in frequency. Here, we proposed a novel GAN-based approach for generating spatio-temporal weather patterns conditioned on detected extreme events. Our approach augments GAN generator and discriminator with an encoded extreme weather event segmentation mask. These segmentation masks can be created from raw input using existing event detection frameworks. As such, our approach is highly modular and can be combined with custom GAN architectures. We highlight the applicability of our proposed approach in experiments with real-world surface radiation and zonal wind data.