Journal article · 2025 · Open access

Generative adversarial models for extreme geospatial downscaling

Guiye Li, Guofeng Cao

International Journal of Applied Earth Observation and Geoinformation, 139, 104541 · Published 1 May 2025 · DOI 10.1016/j.jag.2025.104541

Open full textCite this paper

In brief

“Generative adversarial models for extreme geospatial downscaling” is a 2025 journal article by Guiye Li and Guofeng Cao, published in International Journal of Applied Earth Observation and Geoinformation. OpenAlex counts 17 citations as of 21 November 2026, which puts it in the top 8% of works published in 2025 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at International Journal of Applied Earth Observation and Geoinformation.

Citations
17
Most cited in
2026 (9)
Field-weighted impact
2.69
References
92
Authors
2

Abstract

Addressing the challenges of climate change requires accurate and high-resolution mapping of geospatial data, especially climate and weather variables. However, many existing geospatial datasets, such as the gridded outputs of the state-of-the-art numerical climate models ( e.g ., general circulation models), are only available at very coarse spatial resolutions due to the model complexity and extremely high computational demand. Deep-learning-based methods, particularly generative adversarial networks (GANs) and their variants, have proved effective for refining natural images and have shown great promise in improving geospatial datasets. This paper describes a conditional GAN-based stochastic geospatial downscaling method that can accommodate large scaling factors. Compared to most existing methods, the method can generate high-resolution accurate climate datasets from very low-resolution inputs. More importantly, the method explicitly considers the uncertainty inherent to the downscaling process that tends to be ignored in existing methods. Given an input, the method can produce a multitude of plausible high-resolution samples instead of one single deterministic result. These samples allow for an empirical exploration and inferences of model uncertainty and robustness. With a case study of gridded climate datasets (wind velocity and solar irradiance), we demonstrate the performances of the framework in downscaling tasks with large scaling factors (up to 64 × ) and highlight the advantages of the framework with a comprehensive comparison with commonly used and most recent downscaling methods, including area-to-point (ATP) kriging, deep image prior (DIP), enhanced super-resolution generative adversarial networks (ESRGAN), physics-informed resolution-enhancing GAN (PhIRE GAN), and an efficient diffusion model for remote sensing image super-resolution (EDiffSR). • We present an LAG-based framework for stochastic downscaling of gridded scientific datasets. • We highlight the framework performances with a comprehensive comparison with recent models. • We examine the uncertainty and robustness of the framework with a simulation-based approach.

Cite this paper

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

APA 7

Li, G., & Cao, G. (2025). Generative adversarial models for extreme geospatial downscaling. International Journal of Applied Earth Observation and Geoinformation, 139, 104541. https://doi.org/10.1016/j.jag.2025.104541

MLA 9

Li, Guiye, and Guofeng Cao. “Generative adversarial models for extreme geospatial downscaling.” International Journal of Applied Earth Observation and Geoinformation, vol. 139, 2025, p. 104541. https://doi.org/10.1016/j.jag.2025.104541.

Chicago

Li, Guiye and Guofeng Cao. 2025. “Generative adversarial models for extreme geospatial downscaling.” International Journal of Applied Earth Observation and Geoinformation 139: 104541. https://doi.org/10.1016/j.jag.2025.104541.

Harvard

Li, G. and Cao, G. (2025) ‘Generative adversarial models for extreme geospatial downscaling’, International Journal of Applied Earth Observation and Geoinformation, 139, p. 104541. doi:10.1016/j.jag.2025.104541.

IEEE

G. Li and G. Cao, “Generative adversarial models for extreme geospatial downscaling,” International Journal of Applied Earth Observation and Geoinformation, vol. 139, p. 104541, 2025, doi: 10.1016/j.jag.2025.104541.

BibTeX

@article{li2025generative,
  title     = {{Generative adversarial models for extreme geospatial downscaling}},
  author    = {Li, Guiye and Cao, Guofeng},
  journal   = {International Journal of Applied Earth Observation and Geoinformation},
  year      = {2025},
  volume    = {139},
  pages     = {104541},
  doi       = {10.1016/j.jag.2025.104541},
  url       = {https://doi.org/10.1016/j.jag.2025.104541}
}

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

Citations by year

YearCitationsShare of the best year
202422
202566
202699

Its field-weighted citation impact is 2.69: it has been cited 2.69 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques

  • generative adversarial networks
  • conditional generative adversarial networks
  • stochastic downscaling
  • uncertainty quantification
  • gridded climate data
  • wind speed
  • solar irradiance
  • super-resolution

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, G., & Cao, G. (2025). Generative adversarial models for extreme geospatial downscaling. International Journal of Applied Earth Observation and Geoinformation, 139, 104541. https://doi.org/10.1016/j.jag.2025.104541

How many times has this paper been cited?

17 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 International Journal of Applied Earth Observation and Geoinformation: sign in and open the full text from this page.

Who wrote this paper?

Guiye Li, Guofeng Cao.

What is the DOI of this paper?

10.1016/j.jag.2025.104541, permanently at https://doi.org/10.1016/j.jag.2025.104541. 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.