Geospatial Diffusion-based Evolution Synthesis (GeoDES) for Augmentation of Location-Sparse Phenomena

Geospatial synthesis models are designed to generate realistic environmental conditions, yet they often struggle to capture the detailed dynamics of Location-Sparse Phenomena (LSP): complex events like storms, wildfires and oil spills that occur sparsely and irregularly across the globe. Existing approaches frequently rely on structural simplifications, such as restrictive static regional boundaries or computationally expensive, overly smoothed global grids. Instead, we introduce *Geospatial Diffusion-based Evolution Synthesis (GeoDES)*, a phenomenon-centered spatiotemporal diffusion model. GeoDES' correlated noise schedule, non-autoregressive design and temporal inflative training paradigm serve to increase fidelity and decrease compute requirements for LSP. GeoDES efficiently synthesizes high-quality events to augment hazard datasets and stress-test downstream models. On extratropical cyclone generation tasks, GeoDES outperforms baselines by achieving $21$% lower Peak Vorticity Error and $26$% higher Synoptic Anomaly Correlation Coefficient. Additionally, evaluations on the xBD multi-disaster dataset demonstrate high fidelity, with $41.27$ lower Fréchet Inception Distance than the next-best method. GeoDES brings realistic synthesis to the broad class of LSP and offers a step towards robust geospatial data augmentation.