Journal article · 2025 · Open access

Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations

Elena Tomasi, Gabriele Franch, M. Cristoforetti

Geoscientific model development, 18(6), 2051–2078 · Published 1 April 2025 · DOI 10.5194/gmd-18-2051-2025

Open PDFView at the publisherCite this paper

In brief

“Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations” is a 2025 journal article by Elena Tomasi and 2 co-authors, published in Geoscientific model development. OpenAlex counts 63 citations as of 21 November 2026, which puts it in the top 1% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Geoscientific model development.

Citations
63
Most cited in
2026 (50)
Field-weighted impact
17.36
References
75
Authors
3

Abstract

Downscaling based on deep learning (DL) is a key application in Earth system modeling, enabling the generation of high-resolution fields from coarse numerical simulations at reduced computational costs compared to traditional regional models. Additionally, generative DL models can potentially provide uncertainty quantification through ensemble-like scenario generation, a task prohibitive for conventional numerical approaches. In this study, we apply a latent diffusion model (LDM) to demonstrate that recent advancements in generative modeling enable DL to deliver results comparable to those of numerical dynamical models, given the same input data, preserving the realism of fine-scale features and flow characteristics at reduced computational costs. We apply our LDM to downscale ERA5 data over Italy up to a resolution of 2 km. The high-resolution target data consist of 2 m temperature and 10 m horizontal wind components from a dynamical downscaling performed with COSMO-CLM. A selection of predictors from ERA5 is used as input, and a residual approach against a reference U-Net is leveraged in applying the LDM. The performance of the generative LDM is compared with reference baselines of increasing complexity: a quadratic interpolation of ERA5, a U-Net, and a generative adversarial network (GAN) built on the same reference U-Net. Results highlight the improvements introduced by the LDM architecture combined with the residual approach, outperforming all the baselines in terms of spatial error, frequency distributions, and power spectra. These findings point out the potential of LDMs as cost-effective, robust alternatives for downscaling applications (e.g., downscaling of climate projections), where computational resources are limited but high-resolution data are critical.

Cite this paper

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

APA 7

Tomasi, E., Franch, G., & Cristoforetti, M. (2025). Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations. Geoscientific model development, 18(6), 2051–2078. https://doi.org/10.5194/gmd-18-2051-2025

MLA 9

Tomasi, Elena, et al. “Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations.” Geoscientific model development, vol. 18, no. 6, 2025, pp. 2051–2078. https://doi.org/10.5194/gmd-18-2051-2025.

Chicago

Tomasi, Elena, Gabriele Franch, and M. Cristoforetti. 2025. “Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations.” Geoscientific model development 18 (6): 2051–2078. https://doi.org/10.5194/gmd-18-2051-2025.

Harvard

Tomasi, E., Franch, G. and Cristoforetti, M. (2025) ‘Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations’, Geoscientific model development, 18(6), pp. 2051–2078. doi:10.5194/gmd-18-2051-2025.

IEEE

E. Tomasi, G. Franch, and M. Cristoforetti, “Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations,” Geoscientific model development, vol. 18, no. 6, pp. 2051–2078, 2025, doi: 10.5194/gmd-18-2051-2025.

BibTeX

@article{tomasi2025enabled,
  title     = {{Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0\_CLM9 simulations}},
  author    = {Tomasi, Elena and Franch, Gabriele and Cristoforetti, M.},
  journal   = {Geoscientific model development},
  year      = {2025},
  volume    = {18},
  number    = {6},
  pages     = {2051--2078},
  doi       = {10.5194/gmd-18-2051-2025},
  url       = {https://doi.org/10.5194/gmd-18-2051-2025}
}

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

  • dynamical downscaling
  • latent diffusion models
  • COSMO-CLM
  • ERA5 reanalysis
  • 2 m air temperature
  • 10 m wind speed
  • residual approach
  • U-Net

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?

Tomasi, E., Franch, G., & Cristoforetti, M. (2025). Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations. Geoscientific model development, 18(6), 2051–2078. https://doi.org/10.5194/gmd-18-2051-2025

How many times has this paper been cited?

63 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 Geoscientific model development: sign in and open the PDF from this page.

Who wrote this paper?

Elena Tomasi, Gabriele Franch, M. Cristoforetti.

What is the DOI of this paper?

10.5194/gmd-18-2051-2025, permanently at https://doi.org/10.5194/gmd-18-2051-2025. 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.