Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 19, issue 15
Articles | Volume 19, issue 15
https://doi.org/10.5194/amt-19-5071-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-19-5071-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 15
Research article
 | 
06 Aug 2026
Research article |  | 06 Aug 2026

Improving multi-modal wind speed prediction of short and medium term with a bi-clustered machine learning method

Yan Zhang, Lei Li, Xiong Xiong, Xiang Yin, Xiaojun Zhang, Fuhai Cui, Rui Dang, Wei Liu, Liang Zhai, Pengzhao Wang, Peng Sun, Weixiao Lu, and Wenjie Zhang

Viewed

Total article views: 404 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
252 125 27 404 19 21
  • HTML: 252
  • PDF: 125
  • XML: 27
  • Total: 404
  • BibTeX: 19
  • EndNote: 21
Views and downloads (calculated since 13 Apr 2026)
Cumulative views and downloads (calculated since 13 Apr 2026)

Viewed (geographical distribution)

Total article views: 404 (including HTML, PDF, and XML) Thereof 395 with geography defined and 9 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Aug 2026
Download
Short summary
We developed a Bi-clustered Recursive Bayesian Forest model that improves wind speed forecast accuracy by 48.2 % and reduces error metrics by over 60 %. The model incorporates sea-land breeze, weather stability, and atmospheric circulation indices as features, and uses bi-clustering modal classification to mitigate wind speed magnitude interactions. This machine learning-based correction technique outperforms traditional numerical models, providing more reliable wind speed forecasting.
Read more
Share