Wind Energy Science
Wind Energy Science
WES
Articles | Volume 11, issue 10
Articles | Volume 11, issue 10
https://doi.org/10.5194/wes-11-4041-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-11-4041-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 11, issue 10
Research article
 | 
26 Oct 2026
Research article |  | 26 Oct 2026

The influence of flow-field representation on electrical power and fatigue-load surrogate modelling in offshore wind farms

Pradhyumnaa Ganapathi Subramanian

Viewed

Total article views: 829 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
509 193 127 829 182 145
  • HTML: 509
  • PDF: 193
  • XML: 127
  • Total: 829
  • BibTeX: 182
  • EndNote: 145
Views and downloads (calculated since 04 Feb 2026)
Cumulative views and downloads (calculated since 04 Feb 2026)

Viewed (geographical distribution)

Total article views: 829 (including HTML, PDF, and XML) Thereof 796 with geography defined and 33 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 26 Oct 2026
Download
Short summary
Wind farms need fast ways to predict power and structural fatigue without costly repeated simulations. We compared different representations of wind across a turbine rotor. Spatial averages were sufficient for power, but detailed wind-field information improved predictions for certain fatigue loads. A compact PCA representation achieved the lowest power-prediction error, while a spatial CNN model performed best for fatigue. We show that the most effective approach depends on the prediction task.
Read more
Share
Altmetrics
Final-revised paper
Preprint