Data-driven Mesoscale Weather Forecasting Combining Swin-Unet and Diffusion Models
This work addresses mesoscale weather prediction, particularly for heavy rainfall, with an incremental hybrid approach that maintains flexibility when updating components.
The study tackled mesoscale weather forecasting by combining Swin-Unet with a diffusion model to improve accuracy for heavy rainfall events, achieving better performance as measured by Fractions Skill Score and power spectral analysis compared to predictions without the diffusion model.
Data-driven weather prediction models exhibit promising performance and advance continuously. In particular, diffusion models represent fine-scale details without spatial smoothing, which is crucial for mesoscale predictions, such as heavy rainfall forecasting. However, the applications of diffusion models to mesoscale prediction remain limited. To address this gap, this study proposes an architecture that combines a diffusion model with Swin-Unet as a deterministic model, achieving mesoscale predictions while maintaining flexibility. The proposed architecture trains the two models independently, allowing the diffusion model to remain unchanged when the deterministic model is updated. Comparisons using the Fractions Skill Score and power spectral analysis demonstrate that incorporating the diffusion model leads to improved accuracy compared to predictions without it. These findings underscore the potential of the proposed architecture to enhance mesoscale predictions, particularly for strong rainfall events, while maintaining flexibility.