Preprint · 2025 · Open access

On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling

Paula Harder, Christian Lessig, Matthew Chantry, Pelletier, Francis, David Rolnick

arXiv (Cornell University) · Published 1 December 2025 · DOI 10.48550/arxiv.2512.01400

Open PDFView at the publisherCite this paper

In brief

“On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling” is a 2025 preprint by Paula Harder and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 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
1
Most cited in
2026 (1)
References
25
Authors
5

Abstract

Deep learning offers promising capabilities for the statistical downscaling of climate and weather forecasts, with generative approaches showing particular success in capturing fine-scale precipitation patterns. However, most existing models are region-specific, and their ability to generalize to unseen geographic areas remains largely unexplored. In this study, we evaluate the generalization performance of generative downscaling models across diverse regions. Using a global framework, we employ ERA5 reanalysis data as predictors and IMERG precipitation estimates at $0.1^\circ$ resolution as targets. A hierarchical location-based data split enables a systematic assessment of model performance across 15 regions around the world.

Cite this paper

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

APA 7

Harder, P., Lessig, C., Chantry, M., Francis, P., & Rolnick, D. (2025). On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.01400

MLA 9

Harder, Paula, et al. “On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2512.01400.

Chicago

Harder, Paula, Christian Lessig, Matthew Chantry, Pelletier, Francis, and David Rolnick. 2025. “On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.01400.

Harvard

Harder, P. et al. (2025) ‘On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling’, arXiv (Cornell University). doi:10.48550/arxiv.2512.01400.

IEEE

P. Harder, C. Lessig, M. Chantry, P. Francis, and D. Rolnick, “On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2512.01400.

BibTeX

@misc{harder2025global,
  title     = {{On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling}},
  author    = {Harder, Paula and Lessig, Christian and Chantry, Matthew and Francis, Pelletier, and Rolnick, David},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2512.01400},
  url       = {https://doi.org/10.48550/arxiv.2512.01400}
}

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

  • precipitation downscaling
  • generative deep learning
  • statistical downscaling
  • model generalization
  • ERA5 reanalysis
  • IMERG precipitation

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?

Harder, P., Lessig, C., Chantry, M., Francis, P., & Rolnick, D. (2025). On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.01400

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?

Paula Harder, Christian Lessig, Matthew Chantry, Pelletier, Francis, David Rolnick.

What is the DOI of this paper?

10.48550/arxiv.2512.01400, permanently at https://doi.org/10.48550/arxiv.2512.01400. 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.