EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning in Climate Downscaling: A Critical Review of Methodologies, Physical Consistency, and Operational Applications

Hamed Najafi, Gareth Lynton Lagerwall, Jayantha Obeysekera, Jason Liu

Water · 21.01.2026 · 18 (2) · 271

DOI: 10.3390/w18020271 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 21.01.2026. Verfasst von Hamed Najafi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 184 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution climate projections are essential for regional risk assessment; however, Earth System Models (ESMs) operate at scales far too coarse for local impacts. This review examines how machine learning (ML) downscaling can bridge this divide and addresses a key knowledge gap: how to achieve reliable, physically consistent downscaling under future climate change. This article synthesizes ML downscaling developments from 2010 to 2025, spanning early statistical methods to modern deep learning (e.g., convolutional neural networks (CNNs), generative adversarial networks (GANs), diffusion models, and transformers). The analysis introduces a new taxonomy of model families and frames the discussion around the “performance paradox”—the tendency for models with excellent historical skill to falter under non-stationary climate shifts. Our analysis finds that convolutional approaches efficiently capture spatial structure but tend to smooth out extremes, whereas generative models better reproduce high-intensity events at the cost of greater complexity. The study also highlights emerging solutions like physics-informed models and improved uncertainty quantification to tackle persistent issues of physical consistency and trust. Finally, the synthesis outlines a practical roadmap for operational ML downscaling, emphasizing standardized evaluation, out-of-distribution stress tests, and hybrid physics–ML approaches to bolster confidence in future projections.

Förderung

  • NSF

Zitieren

APA

Najafi, H., Lagerwall, G. L., Obeysekera, J., & Liu, J. (2026). Machine Learning in Climate Downscaling: A Critical Review of Methodologies, Physical Consistency, and Operational Applications. Water, 18(2), 271. https://doi.org/10.3390/w18020271

Vancouver

Najafi H, Lagerwall GL, Obeysekera J, Liu J. Machine Learning in Climate Downscaling: A Critical Review of Methodologies, Physical Consistency, and Operational Applications. Water. 2026;18(2):271. doi:10.3390/w18020271

BibTeX
@article{Najafi2026,
  author = {Najafi, Hamed and Lagerwall, Gareth Lynton and Obeysekera, Jayantha and Liu, Jason},
  title = {Machine Learning in Climate Downscaling: A Critical Review of Methodologies, Physical Consistency, and Operational Applications},
  journal = {Water},
  year = {2026},
  volume = {18},
  number = {2},
  pages = {271},
  doi = {10.3390/w18020271}
}
Kostenlos starten →