Preprint · 2024 · Open access

Generative Diffusion-based Downscaling for Climate

Robbie Watt, Laura Mansfield

arXiv (Cornell University) · Published 27 April 2024 · DOI 10.48550/arxiv.2404.17752

Open PDFView at the publisherCite this paper

In brief

“Generative Diffusion-based Downscaling for Climate” is a 2024 preprint by Robbie Watt and Laura Mansfield, published in arXiv (Cornell University). OpenAlex counts 61 citations as of 21 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
61
Most cited in
2026 (41)
References
82
Authors
2

Abstract

Downscaling, or super-resolution, provides decision-makers with detailed, high-resolution information about the potential risks and impacts of climate change, based on climate model output. Machine learning algorithms are proving themselves to be efficient and accurate approaches to downscaling. Here, we show how a generative, diffusion-based approach to downscaling gives accurate downscaled results. We focus on an idealised setting where we recover ERA5 at $0.25\degree$~resolution from coarse grained version at $2\degree$~resolution. The diffusion-based method provides superior accuracy compared to a standard U-Net, particularly at the fine scales, as highlighted by a spectral decomposition. Additionally, the generative approach provides users with a probability distribution which can be used for risk assessment. This research highlights the potential of diffusion-based downscaling techniques in providing reliable and detailed climate predictions.

Cite this paper

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

APA 7

Watt, R., & Mansfield, L. (2024). Generative Diffusion-based Downscaling for Climate. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2404.17752

MLA 9

Watt, Robbie, and Laura Mansfield. “Generative Diffusion-based Downscaling for Climate.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2404.17752.

Chicago

Watt, Robbie and Laura Mansfield. 2024. “Generative Diffusion-based Downscaling for Climate.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2404.17752.

Harvard

Watt, R. and Mansfield, L. (2024) ‘Generative Diffusion-based Downscaling for Climate’, arXiv (Cornell University). doi:10.48550/arxiv.2404.17752.

IEEE

R. Watt and L. Mansfield, “Generative Diffusion-based Downscaling for Climate,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2404.17752.

BibTeX

@misc{watt2024generative,
  title     = {{Generative Diffusion-based Downscaling for Climate}},
  author    = {Watt, Robbie and Mansfield, Laura},
  howpublished = {arXiv (Cornell University)},
  year      = {2024},
  doi       = {10.48550/arxiv.2404.17752},
  url       = {https://doi.org/10.48550/arxiv.2404.17752}
}

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

Citations by year

YearCitationsShare of the best year
202444
20251616
20264141

Topic and keywords

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

  • climate downscaling
  • super-resolution
  • generative diffusion models
  • ERA5 reanalysis
  • U-Net comparison
  • spectral decomposition
  • climate risk assessment
  • probability distributions

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?

Watt, R., & Mansfield, L. (2024). Generative Diffusion-based Downscaling for Climate. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2404.17752

How many times has this paper been cited?

61 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?

Robbie Watt, Laura Mansfield.

What is the DOI of this paper?

10.48550/arxiv.2404.17752, permanently at https://doi.org/10.48550/arxiv.2404.17752. 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.