Preprint · 2025 · Open access

Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling

Saccardi, Carlo, Maximilian Pierzyna, Haitz Sáez de Ocáriz Borde, Monaco, Simone, Cristian Meo, Píetro Lió, Rudolf Saathof, Geethu Joseph, Justin Dauwels

arXiv (Cornell University) · Published 15 October 2025 · DOI 10.48550/arxiv.2510.13722

Open PDFView at the publisherCite this paper

In brief

“Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling” is a 2025 preprint by Saccardi, Carlo and 8 co-authors, published in arXiv (Cornell University). OpenAlex counts 8 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
8
Most cited in
2026 (6)
References
35
Authors
9

Abstract

Kilometer-scale weather data is crucial for real-world applications but remains computationally intensive to produce using traditional weather simulations. An emerging solution is to use deep learning models, which offer a faster alternative for climate downscaling. However, their reliability is still in question, as they are often evaluated using standard machine learning metrics rather than insights from atmospheric and weather physics. This paper benchmarks recent state-of-the-art deep learning models and introduces physics-inspired diagnostics to evaluate their performance and reliability, with a particular focus on geographic generalization and physical consistency. Our experiments show that, despite the seemingly strong performance of models such as CorrDiff, when trained on a limited set of European geographies (e.g., central Europe), they struggle to generalize to other regions such as Iberia, Morocco in the south, or Scandinavia in the north. They also fail to accurately capture second-order variables such as divergence and vorticity derived from predicted velocity fields. These deficiencies appear even in in-distribution geographies, indicating challenges in producing physically consistent predictions. We propose a simple initial solution: introducing a power spectral density loss function that empirically improves geographic generalization by encouraging the reconstruction of small-scale physical structures. The code for reproducing the experimental results can be found at https://github.com/CarloSaccardi/PSD-Downscaling

Cite this paper

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

APA 7

Carlo, S., Pierzyna, M., Borde, H. S. D. O., Simone, M., Meo, C., Lió, P., Saathof, R., Joseph, G., & Dauwels, J. (2025). Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.13722

MLA 9

Carlo, Saccardi,, et al. “Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2510.13722.

Chicago

Carlo, Saccardi,, Maximilian Pierzyna, Haitz Sáez de Ocáriz Borde, Monaco, Simone, Cristian Meo, Píetro Lió, Rudolf Saathof, Geethu Joseph, and Justin Dauwels. 2025. “Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.13722.

Harvard

Carlo, S. et al. (2025) ‘Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling’, arXiv (Cornell University). doi:10.48550/arxiv.2510.13722.

IEEE

S. Carlo et al., “Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2510.13722.

BibTeX

@misc{carlo2025assessing,
  title     = {{Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling}},
  author    = {Carlo, Saccardi, and Pierzyna, Maximilian and Borde, Haitz Sáez de Ocáriz and Simone, Monaco, and Meo, Cristian and Lió, Píetro and Saathof, Rudolf and Joseph, Geethu and Dauwels, Justin},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2510.13722},
  url       = {https://doi.org/10.48550/arxiv.2510.13722}
}

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
  • model benchmarking

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?

Carlo, S., Pierzyna, M., Borde, H. S. D. O., Simone, M., Meo, C., Lió, P., Saathof, R., Joseph, G., & Dauwels, J. (2025). Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.13722

How many times has this paper been cited?

8 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?

Saccardi, Carlo, Maximilian Pierzyna, Haitz Sáez de Ocáriz Borde, Monaco, Simone, Cristian Meo, Píetro Lió, Rudolf Saathof, Geethu Joseph, Justin Dauwels.

What is the DOI of this paper?

10.48550/arxiv.2510.13722, permanently at https://doi.org/10.48550/arxiv.2510.13722. 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.