Conference paper · 2025 · Open access

Application of novel generative diffusion models to precipitation downscaling

Alex A Saoulis, Jorge Sebastián Moraga, Natalie S. Lord, Peter F. Uhe, Nans Addor

EGU General Assembly Conference Abstracts · Published 20 January 2025 · DOI 10.5194/egusphere-egu24-19266

Open full textCite this paper

In brief

“Application of novel generative diffusion models to precipitation downscaling” is a 2025 conference paper by Alex A Saoulis and 4 co-authors, published in EGU General Assembly Conference Abstracts. 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 EGU General Assembly Conference Abstracts.

Citations
1
Most cited in
2025 (1)
Authors
5

Abstract

Machine Learning (ML) is playing an increasingly valuable role in statistical downscaling. Capable of leveraging complex, non-linear relationships latent in the training data, the community has demonstrated significant potential for ML to learn a downscaling mapping. Following the perfect-prognosis (PP) approach, ML models can be trained on historical reanalysis data to learn a relationship between coarse predictors and higher resolution (i.e. downscaled) predictands. Once trained, the models can then be evaluated on general circulation model (GCM) outputs to generate regional downscaled results. Due to the relatively low computational cost of training and utilising these models, they can be used to efficiently downscale large ensembles of climate models over regional to global domains.This work employs a novel diffusion algorithm to downscale climate data. Diffusion models have proven highly successful in applications such as natural image generation and super-resolution (the natural image analogue to climate downscaling). Diffusion models have been shown to significantly outperform earlier generative ML models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs); they can produce highly diverse samples, emulate fine details with high fidelity, and exhibit much more stable training than alternative ML models. This work trains and evaluates diffusion models on the Multi-Source Weighted-Ensemble Precipitation (MSWEP) observational dataset over the Colorado River Basin (USA). High resolution (10km x 10km) MSWEP fields are artificially coarsened to generate training data. Once trained, the models are applied to bias-corrected climate model outputs to evaluate their ability to generate realistic downscaled precipitation fields. Performance is compared with several benchmarks, including classical regression techniques as well as alternative ML models.

Cite this paper

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

APA 7

Saoulis, A. A., Moraga, J. S., Lord, N. S., Uhe, P. F., & Addor, N. (2025). Application of novel generative diffusion models to precipitation downscaling. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu24-19266

MLA 9

Saoulis, Alex A, et al. “Application of novel generative diffusion models to precipitation downscaling.” EGU General Assembly Conference Abstracts, 2025. https://doi.org/10.5194/egusphere-egu24-19266.

Chicago

Saoulis, Alex A, Jorge Sebastián Moraga, Natalie S. Lord, Peter F. Uhe, and Nans Addor. 2025. “Application of novel generative diffusion models to precipitation downscaling.” EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu24-19266.

Harvard

Saoulis, A. A. et al. (2025) ‘Application of novel generative diffusion models to precipitation downscaling’, EGU General Assembly Conference Abstracts. doi:10.5194/egusphere-egu24-19266.

IEEE

A. A. Saoulis, J. S. Moraga, N. S. Lord, P. F. Uhe, and N. Addor, “Application of novel generative diffusion models to precipitation downscaling,” EGU General Assembly Conference Abstracts, 2025, doi: 10.5194/egusphere-egu24-19266.

BibTeX

@inproceedings{saoulis2025application,
  title     = {{Application of novel generative diffusion models to precipitation downscaling}},
  author    = {Saoulis, Alex A and Moraga, Jorge Sebastián and Lord, Natalie S. and Uhe, Peter F. and Addor, Nans},
  booktitle = {EGU General Assembly Conference Abstracts},
  year      = {2025},
  doi       = {10.5194/egusphere-egu24-19266},
  url       = {https://doi.org/10.5194/egusphere-egu24-19266}
}

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

  • precipitation downscaling
  • generative diffusion models
  • climate model bias correction
  • Colorado River Basin
  • super-resolution
  • dynamical downscaling

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?

Saoulis, A. A., Moraga, J. S., Lord, N. S., Uhe, P. F., & Addor, N. (2025). Application of novel generative diffusion models to precipitation downscaling. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu24-19266

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 EGU General Assembly Conference Abstracts: sign in and open the full text from this page.

Who wrote this paper?

Alex A Saoulis, Jorge Sebastián Moraga, Natalie S. Lord, Peter F. Uhe, Nans Addor.

What is the DOI of this paper?

10.5194/egusphere-egu24-19266, permanently at https://doi.org/10.5194/egusphere-egu24-19266. 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.