Predicting forecast errors with diffusion model for uncertainty quantification in wind speed nowcasting

Zhu, Yanwei; Atencia, Aitor; Dabernig, Markus; Wang, Yong; Zhou, Shuyan

doi:10.5194/gmd-19-7835-2026

Articles | Volume 19, issue 16

https://doi.org/10.5194/gmd-19-7835-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-19-7835-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 16

Development and technical paper

|

24 Aug 2026

Development and technical paper |

| 24 Aug 2026

Predicting forecast errors with diffusion model for uncertainty quantification in wind speed nowcasting

Yanwei Zhu, Aitor Atencia, Markus Dabernig, Yong Wang, and Shuyan Zhou

Supplement

https://doi.org/10.5194/gmd-19-7835-2026-supplement

Data sets

Dataset for denoising diffusion probabilistic model to generate 10-m wind speed ensemble nowcast Yanwei Zhu https://doi.org/10.5281/zenodo.19029542

Model code and software

Code for denoising diffusion probabilistic model to generate 10-m wind speed ensemble nowcast Yanwei Zhu https://doi.org/10.5281/zenodo.19673041

Short summary

The study proposes a diffusion-based framework for uncertainty quantification in wind speed nowcasting by learning forecast error distributions. By randomly generating errors and adding them to a physics-based wind nowcast, multiple forecast scenarios can be produced. The results improve forecast accuracy and provide reliable estimates of forecast uncertainty.