Articles | Volume 11, issue 8
https://doi.org/10.5194/wes-11-2869-2026
https://doi.org/10.5194/wes-11-2869-2026
Research article
 | 
11 Aug 2026
Research article |  | 11 Aug 2026

Convolutional versus graph-based surrogate models for inter-farm wake prediction using multi-fidelity transfer learning

Jens Peter Schøler, Frederik Peder Weilmann Rasmussen, M. Paul van der Laan, Alfredo Peña, and Pierre-Elouan Réthoré

Data sets

RANS-AWF Random Cluster Layouts M. P. van der Laan et al. https://doi.org/10.5281/zenodo.20543178

Wind farm: Graph flow test data J. P. Schøler et al. https://doi.org/10.5281/zenodo.17671257

Model code and software

Wind-Farm-ARU-Net Frederik Peder Weilmann Rasmussen https://github.com/FPWRasmussen/Wind-Farm-ARU-Net

Download
Short summary
As offshore wind farms are built closer together, predicting how they affect each other becomes critical. We compared two AI approaches for this task, training both on cheap approximate data before refining them with expensive high-accuracy simulations. One predicts wake boundaries better, while the other estimates wind speeds more accurately, offering complementary tools for future wind farm design.
Share
Altmetrics
Final-revised paper
Preprint