EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative unsupervised downscaling of climate models via domain alignment: Application to wind fields

Julie Keisler, Boutheina Oueslati, Anastase Charantonis, Yannig Goude, Claire Monteleoni

Environmental Data Science · 2026 · 5

DOI: 10.1017/eds.2026.10057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Data Science, online erschienen am 17.07.2026. Verfasst von Julie Keisler und 4 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

General circulation models (GCMs) are widely used for future climate projections, but their coarse spatial resolution and systematic biases limit their direct use for impact studies. This limitation is particularly critical for wind-related applications, such as wind energy, which require spatially coherent, multivariate, and physically plausible near-surface wind fields. Classical statistical downscaling and bias correction methods partly address this issue. Still, they struggle to preserve spatial structure, intervariable consistency, and robustness under climate change, especially in high-dimensional settings. Recent advances in generative machine learning offer new opportunities for downscaling and bias correction, eliminating the need for explicitly paired low- and high-resolution datasets. However, many existing approaches remain difficult to interpret and challenging to deploy in operational climate impact studies. In this work, we apply SerpentFlow, an interpretable, generative, domain alignment framework, to the multivariate downscaling and bias correction of wind variables from GCM outputs. This is a method that generates low-resolution/high-resolution training data pairs by separating large-scale spatial patterns from small-scale variability. Large-scale components are aligned across climate model and observational domains. Conditional fine-scale variability is then learned using a flow-matching generative model. We apply the approach to multiple wind variables downscaling, including average and maximal wind speed, zonal and meridional components, and compare it with widely used multivariate bias correction methods. Results show improved spatial coherence, intervariable consistency, and robustness under future climate conditions, highlighting the potential of interpretable generative models for wind and energy applications.

Zitieren

APA

Keisler, J., Oueslati, B., Charantonis, A., Goude, Y., & Monteleoni, C. (2026). Generative unsupervised downscaling of climate models via domain alignment: Application to wind fields. Environmental Data Science, 5. https://doi.org/10.1017/eds.2026.10057

Vancouver

Keisler J, Oueslati B, Charantonis A, Goude Y, Monteleoni C. Generative unsupervised downscaling of climate models via domain alignment: Application to wind fields. Environmental Data Science. 2026;5. doi:10.1017/eds.2026.10057

BibTeX
@article{Keisler2026,
  author = {Keisler, Julie and Oueslati, Boutheina and Charantonis, Anastase and Goude, Yannig and Monteleoni, Claire},
  title = {Generative unsupervised downscaling of climate models via domain alignment: Application to wind fields},
  journal = {Environmental Data Science},
  year = {2026},
  volume = {5},
  doi = {10.1017/eds.2026.10057}
}
Kostenlos starten →