Controlling Ensemble Variance in Diffusion Models: An Application for Reanalyses Downscaling
Merizzi, Fabio, Evangelista, Davide, Loukos, Harilaos
–arXiv.org Artificial Intelligence
In recent years, diffusion models have emerged as powerful tools for generating ensemble members in meteorology. In this work, we demonstrate that a Denoising Diffusion Implicit Model (DDIM) can effectively control ensemble variance by varying the number of diffusion steps. Introducing a theoretical framework, we relate diffusion steps to the variance expressed by the reverse diffusion process. Focusing on reanalysis downscaling, we propose an ensemble diffusion model for the full ERA5-to-CERRA domain, generating variance-calibrated ensemble members for wind speed at full spatial and temporal resolution. Our method aligns global mean variance with a reference ensemble dataset and ensures spatial variance is distributed in accordance with observed meteorological variability. Additionally, we address the lack of ensemble information in the CARRA dataset, showcasing the utility of our approach for efficient, high-resolution ensemble generation.
arXiv.org Artificial Intelligence
Jan-21-2025
- Country:
- Arctic Ocean > Barents Sea (0.04)
- Asia
- Central Asia (0.04)
- China (0.04)
- Atlantic Ocean > North Atlantic Ocean
- Baffin Bay (0.04)
- Greenland Sea (0.04)
- Labrador Sea (0.04)
- Norwegian Sea (0.04)
- Europe
- Denmark (0.14)
- France > Île-de-France
- Iceland (0.04)
- Italy > Emilia-Romagna
- Metropolitan City of Bologna > Bologna (0.04)
- Norway (0.04)
- Sweden (0.04)
- North America
- Canada > Newfoundland and Labrador
- Labrador (0.04)
- Greenland (0.04)
- Canada > Newfoundland and Labrador
- Genre:
- Research Report > New Finding (0.93)
- Technology: