Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 19, issue 18
Articles | Volume 19, issue 18
https://doi.org/10.5194/gmd-19-9235-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-19-9235-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 18
Model description paper
 | 
29 Sep 2026
Model description paper |  | 29 Sep 2026

China regional 3 km downscaling based on residual Corrective Diffusion model

Honglu Sun, Hao Jing, Zhixiang Dai, Sa Xiao, Wei Xue, Jian Sun, and Qifeng Lu

Viewed

Total article views: 2,419 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,394 915 110 2,419 75 131
  • HTML: 1,394
  • PDF: 915
  • XML: 110
  • Total: 2,419
  • BibTeX: 75
  • EndNote: 131
Views and downloads (calculated since 25 Feb 2026)
Cumulative views and downloads (calculated since 25 Feb 2026)

Viewed (geographical distribution)

Total article views: 2,419 (including HTML, PDF, and XML) Thereof 2,385 with geography defined and 34 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 29 Sep 2026
Download
Short summary
This study represents the first application of CorrDiff (Corrective Diffusion), a diffusion-based model, to achieve 3 km resolution statistical downscaling over China by integrating various variables at multiple levels. Through structural improvements to CorrDiff, our methods produce forecasts that outperform the China Meteorological Administration Mesoscale Model for almost all target variables. Our results show that for radar reflectivity prediction, CorrDiff yields more realistic outputs than regression models.
Read more
Share