Preprint · 2026 · Open access

Physics-Constrained Adaptive Flow Matching for Climate Downscaling

Kevin Debeire, Aytaç Paçal, Pierre Gentine, Luis Medrano-Navarro, Nils Thuerey, Veronika Eyring

arXiv (Cornell University) · Published 3 April 2026 · DOI 10.48550/arxiv.2604.03459

Open PDFView at the publisherCite this paper

In brief

“Physics-Constrained Adaptive Flow Matching for Climate Downscaling” is a 2026 preprint by Kevin Debeire and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 4 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
4
Most cited in
2026 (4)
References
27
Authors
6

Abstract

Regional climate information at kilometer scales is essential for assessing the impacts of climate change, but generating it with global climate models is too expensive due to their high computational costs. Machine learning models offer a fast alternative, yet they often violate basic physical laws and degrade when applied to climates outside of their training distribution. We present Physics-Constrained Adaptive Flow Matching (PC-AFM), a generative downscaling model that addresses both problems. Building on the Adaptive Flow Matching (AFM) model of Fotiadis et al. (2025) as our baseline, we add soft conservation constraints that keep the downscaled output consistent with the large-scale input for precipitation and humidity, and use gradient surgery via the ConFIG algorithm to prevent these constraints from interfering with the generative objective. We train the model on Central Europe climate data, evaluate it on a 10-time downscaling task (63km to 6.3km) over six variables (near-surface temperature, precipitation, specific humidity, surface pressure, and horizontal wind components) across a comprehensive set of metrics including bias, ensemble skill scores, power spectra, and conservation error, and test the generalization on two held-out climate regions. Within the training distribution, PC-AFM reduces conservation errors and improves ensemble calibration while matching the baseline on standard skill metrics. Outside the training distribution, where unconstrained models develop large systematic errors by extrapolating learned statistics, PC-AFM halves precipitation wet bias, reduces conservation error and improves extreme-quantile accuracy, all without any information about the target climate at inference time. These results indicate that physical consistency is a practical requirement for deploying generative downscaling models in real-world applications.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Debeire, K., Paçal, A., Gentine, P., Medrano-Navarro, L., Thuerey, N., & Eyring, V. (2026). Physics-Constrained Adaptive Flow Matching for Climate Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.03459

MLA 9

Debeire, Kevin, et al. “Physics-Constrained Adaptive Flow Matching for Climate Downscaling.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2604.03459.

Chicago

Debeire, Kevin, Aytaç Paçal, Pierre Gentine, Luis Medrano-Navarro, Nils Thuerey, and Veronika Eyring. 2026. “Physics-Constrained Adaptive Flow Matching for Climate Downscaling.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.03459.

Harvard

Debeire, K. et al. (2026) ‘Physics-Constrained Adaptive Flow Matching for Climate Downscaling’, arXiv (Cornell University). doi:10.48550/arxiv.2604.03459.

IEEE

K. Debeire, A. Paçal, P. Gentine, L. Medrano-Navarro, N. Thuerey, and V. Eyring, “Physics-Constrained Adaptive Flow Matching for Climate Downscaling,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2604.03459.

BibTeX

@misc{debeire2026physics,
  title     = {{Physics-Constrained Adaptive Flow Matching for Climate Downscaling}},
  author    = {Debeire, Kevin and Paçal, Aytaç and Gentine, Pierre and Medrano-Navarro, Luis and Thuerey, Nils and Eyring, Veronika},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2604.03459},
  url       = {https://doi.org/10.48550/arxiv.2604.03459}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • climate downscaling
  • physical consistency
  • regional climate
  • ensemble calibration
  • extreme quantiles

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Debeire, K., Paçal, A., Gentine, P., Medrano-Navarro, L., Thuerey, N., & Eyring, V. (2026). Physics-Constrained Adaptive Flow Matching for Climate Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.03459

How many times has this paper been cited?

4 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Kevin Debeire, Aytaç Paçal, Pierre Gentine, Luis Medrano-Navarro, Nils Thuerey, Veronika Eyring.

What is the DOI of this paper?

10.48550/arxiv.2604.03459, permanently at https://doi.org/10.48550/arxiv.2604.03459. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.