EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Super-resolving coarse-resolution weather forecasts with flow matching

Aymeric Delefosse, Anastase Charantonis, Dominique Béréziat

Environmental Data Science · 2026 · 5

DOI: 10.1017/eds.2026.10046 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Data Science, online erschienen am 06.08.2026. Verfasst von Aymeric Delefosse und 2 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministère de l'Enseignement supérieur et de la Recherche, Agence Nationale de la Recherche, Grand Équipement National De Calcul Intensif.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Ministère de l'Enseignement supérieur et de la Recherche
  • Agence Nationale de la Recherche
  • Grand Équipement National De Calcul Intensif

Zitieren

APA

Delefosse, A., Charantonis, A., & Béréziat, D. (2026). Super-resolving coarse-resolution weather forecasts with flow matching. Environmental Data Science, 5. https://doi.org/10.1017/eds.2026.10046

Vancouver

Delefosse A, Charantonis A, Béréziat D. Super-resolving coarse-resolution weather forecasts with flow matching. Environmental Data Science. 2026;5. doi:10.1017/eds.2026.10046

BibTeX
@article{Delefosse2026,
  author = {Delefosse, Aymeric and Charantonis, Anastase and Béréziat, Dominique},
  title = {Super-resolving coarse-resolution weather forecasts with flow matching},
  journal = {Environmental Data Science},
  year = {2026},
  volume = {5},
  doi = {10.1017/eds.2026.10046}
}
Kostenlos starten →