Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 19, issue 16
Articles | Volume 19, issue 16
https://doi.org/10.5194/gmd-19-7545-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-19-7545-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 16
Model evaluation paper
 | 
17 Aug 2026
Model evaluation paper |  | 17 Aug 2026

Comprehensive inter-comparison of generative AI models for super-resolution precipitation downscaling across hydroclimatic regimes

Shivam Singh, Simon Michael Papalexiou, Hebatallah M. Abdelmoaty, Tom Hartvigsen, and Antonios Mamalakis

Viewed

Total article views: 2,400 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,452 844 104 2,400 2,271 77 123
  • HTML: 1,452
  • PDF: 844
  • XML: 104
  • Total: 2,400
  • Supplement: 2,271
  • BibTeX: 77
  • EndNote: 123
Views and downloads (calculated since 27 Feb 2026)
Cumulative views and downloads (calculated since 27 Feb 2026)

Viewed (geographical distribution)

Total article views: 2,400 (including HTML, PDF, and XML) Thereof 2,362 with geography defined and 38 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 17 Aug 2026
Download
Short summary
High-resolution precipitation is critical for hydrologic and climate-risk applications, but climate models are too coarse to resolve storm-scale extremes. We compare a deterministic U-NET with two generative models, a Wasserstein Generative Adversarial Network (WGAN) and a diffusion model, for 8× and 16× precipitation downscaling using ERA5-Land. U-NET is stable but smooths extremes, whereas generative models better capture variability and heavy tails while introducing greater uncertainty.
Read more
Share