Communication Dans Un Congrès Année : 2026

Super-Resolving Coarse-Resolution Weather Forecasts with Flow Matching

Résumé

Machine learning-based weather forecasting models now surpass state-of-the-art numerical weather prediction systems, but training and operating these models at high spatial resolution remains computationally expensive. We present a modular framework that decouples forecasting from spatial resolution by applying learned generative super-resolution as a post-processing step to coarse-resolution forecast trajectories. We formulate super-resolution as a stochastic inverse problem, using a residual formulation to preserve large-scale structure while reconstructing unresolved variability. The model is trained with flow matching exclusively on reanalysis data and is applied to global medium-range forecasts. We evaluate (i) design consistency by re-coarsening super-resolved forecasts and comparing them to the original coarse trajectories, and (ii) high-resolution forecast quality using standard ensemble verification metrics and spectral diagnostics. Results show that super-resolution preserves large-scale structure and variance after re-coarsening, introduces physically consistent small-scale variability, and achieves competitive probabilistic forecast skill at 0.25°resolution relative to an operational ensemble baseline, while requiring only a modest additional training cost compared with end-to-end high-resolution forecasting.

Impact Statement

This article shows how learned super-resolution can enhance the spatial detail of coarse-resolution weather forecasts without retraining forecasting models at operational resolution. The approach reduces computational requirements, making high-resolution weather products more accessible in research and operational settings with limited resources.

Fichier principal
Vignette du fichier
camera_ready_submission_uncompressed.pdf (7.23 Mo) Télécharger le fichier
Origine Publication financée par une institution
Licence

Dates et versions

hal-05577032 , version 1 (02-04-2026)
hal-05577032 , version 2 (09-04-2026)

Licence

Identifiants

  • HAL Id : hal-05577032 , version 2

Citer

Aymeric Delefosse, Anastase Charantonis, Dominique Béréziat. Super-Resolving Coarse-Resolution Weather Forecasts with Flow Matching. Climate Informatics 2026 - 15th International Conference on Climate Informatics, Apr 2026, Lausanne, Switzerland. ⟨hal-05577032v2⟩
275 Consultations
79 Téléchargements

Partager

  • More