Preprint · 2026 · Open access

Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?

Mikel N. Legasa, Antoine Doury, Achille Gellens, Redouane Lguensat, Clara Naldesi, Soulivanh Thao, Mathieu Vrac

arXiv (Cornell University) · Published 12 June 2026 · DOI 10.48550/arxiv.2606.14570

Open PDFView at the publisherCite this paper

In brief

“Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?” is a 2026 preprint by Mikel N. Legasa and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 21 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
40
Authors
7

Abstract

Emulators provide a cost-effective alternative to regional climate models (RCMs) by capturing their dynamical downscaling function. They link large-scale predictors simulated by global climate models (GCMs) to RCM-simulated high-resolution fields of the target variable, here precipitation. Machine learning methods, typically deep learning, are cheaper than running RCMs in computation time and energy. Among them, generative models are appealing because they can simulate ensembles of local high-resolution fields consistent with the predictors. This ensemble, which we call the uncertainty envelope, remains to be properly assessed for added value. Here, we make three contributions. First, we introduce ParamDiffusion, a new two-stage diffusion-based framework, and compare it with a state-of-the-art diffusion approach. Second, we expand standard validation through a comprehensive framework aligned with climate-science needs, examining specific precipitation events, including extremes. Third, within this framework, we assess the added value of diffusion approaches relative to deterministic methods. We intercompare four deep-learning models: a deterministic model designed to capture the precipitation tail; a parametric probabilistic model based on it; a recently proposed diffusion approach; and ParamDiffusion, which couples the parametric model with a diffusion model. Our results show that diffusion-based approaches reproduce climatological precipitation statistics with high skill, including distributional tails and spatially compounded extremes, while generating spatially detailed fields. However, none of the assessed models consistently accounts for the most extreme RCM-simulated events within its uncertainty envelope. Diffusion models are therefore promising for probabilistic RCM emulation, but progress is still required before they can reliably represent high-impact precipitation extremes.

Cite this paper

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

APA 7

Legasa, M. N., Doury, A., Gellens, A., Lguensat, R., Naldesi, C., Thao, S., & Vrac, M. (2026). Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.14570

MLA 9

Legasa, Mikel N., et al. “Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2606.14570.

Chicago

Legasa, Mikel N., Antoine Doury, Achille Gellens, Redouane Lguensat, Clara Naldesi, Soulivanh Thao, and Mathieu Vrac. 2026. “Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.14570.

Harvard

Legasa, M. N. et al. (2026) ‘Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?’, arXiv (Cornell University). doi:10.48550/arxiv.2606.14570.

IEEE

M. N. Legasa et al., “Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2606.14570.

BibTeX

@misc{legasa2026regional,
  title     = {{Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?}},
  author    = {Legasa, Mikel N. and Doury, Antoine and Gellens, Achille and Lguensat, Redouane and Naldesi, Clara and Thao, Soulivanh and Vrac, Mathieu},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2606.14570},
  url       = {https://doi.org/10.48550/arxiv.2606.14570}
}

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

Topic and keywords

Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models

  • diffusion models
  • heavy rainfall

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Legasa, M. N., Doury, A., Gellens, A., Lguensat, R., Naldesi, C., Thao, S., & Vrac, M. (2026). Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.14570

How many times has this paper been cited?

1 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?

Mikel N. Legasa, Antoine Doury, Achille Gellens, Redouane Lguensat, Clara Naldesi, Soulivanh Thao, Mathieu Vrac.

What is the DOI of this paper?

10.48550/arxiv.2606.14570, permanently at https://doi.org/10.48550/arxiv.2606.14570. 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.