Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

TL;DR

This paper presents a diffusion-based probabilistic method for atmospheric downscaling, transforming low-resolution forecasts into high-resolution ensembles while capturing small-scale details and extremes.

Contribution

The novel approach uses diffusion models within the Anemoi framework to learn the conditional distribution of residuals for high-resolution weather downscaling.

Findings

Increases probabilistic skill (FCRPS) for surface variables.

Reproduces target power spectra at small scales.

Captures physically consistent multivariate relationships and extremes.

Abstract

We introduce a probabilistic diffusion-based method for global atmospheric downscaling implemented within the Anemoi framework. The approach transforms low-resolution ensemble forecasts into high-resolution ensembles by learning the conditional distribution of finer-scale residuals, defined as the difference between the high-resolution fields and the interpolated low-resolution inputs. The system is trained on reforecast pairs from ECMWF IFS, using coarse fields at 100 km to reconstruct fine-scale variability at 30 km resolution. The bulk of the training focuses on recovering small-scale structures, while fine-tuning in high-noise regimes enables the generation of extremes. Evaluation against the medium-range IFS ensemble target shows that the model increases probabilistic skill (FCRPS) for surface variables, reproduces target power spectra at small scales, captures physically consistent multivariate relationships such as wind-pressure coupling, and generates extreme values consistent with those of the target ensemble in tropical cyclones.