EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Computing the Ensemble Spread From Deterministic Weather Predictions Using Conditional Generative Adversarial Networks

Rüdiger Brecht, Alex Bihlo

Geophysical Research Letters · 28.01.2023 · 50 (2)

DOI: 10.1029/2022gl101452 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 18.01.2023. Verfasst von Rüdiger Brecht und 1 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Natural Sciences and Engineering Research Council of Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensemble prediction systems are an invaluable tool for weather forecasting. Practically, ensemble predictions are obtained by running several perturbations of the deterministic control forecast. However, ensemble prediction is associated with a high computational cost and often involves statistical post‐processing steps to improve its quality. Here we propose to use deep‐learning‐based algorithms to learn the statistical properties of an ensemble prediction system, the ensemble spread, given only the deterministic control forecast. Thus, once trained, the costly ensemble prediction system will not be needed anymore to obtain future ensemble forecasts, and the statistical properties of the ensemble can be derived from a single deterministic forecast. We adapt the classical pix2pix architecture to a three‐dimensional model and train them against several years of operational (ensemble) weather forecasts for the 500 hPa geopotential height. The results demonstrate that the trained models indeed allow obtaining a highly accurate ensemble spread from the control forecast only.

Förderung

  • Deutsche Forschungsgemeinschaft
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Brecht, R., & Bihlo, A. (2023). Computing the Ensemble Spread From Deterministic Weather Predictions Using Conditional Generative Adversarial Networks. Geophysical Research Letters, 50(2). https://doi.org/10.1029/2022gl101452

Vancouver

Brecht R, Bihlo A. Computing the Ensemble Spread From Deterministic Weather Predictions Using Conditional Generative Adversarial Networks. Geophysical Research Letters. 2023;50(2). doi:10.1029/2022gl101452

BibTeX
@article{Brecht2023,
  author = {Brecht, Rüdiger and Bihlo, Alex},
  title = {Computing the Ensemble Spread From Deterministic Weather Predictions Using Conditional Generative Adversarial Networks},
  journal = {Geophysical Research Letters},
  year = {2023},
  volume = {50},
  number = {2},
  doi = {10.1029/2022gl101452}
}
Kostenlos starten →