Articles | Volume 22
https://doi.org/10.5194/asr-22-59-2025
https://doi.org/10.5194/asr-22-59-2025
21 Oct 2025
 | 21 Oct 2025

Improving wind power forecasts in the Belgian North Sea with a wind farm parameterization and a neural network

Dieter Van den Bleeken, Geert Smet, Joris Van den Bergh, Idir Dehmous, Daan Degrauwe, Michiel Van Ginderachter, and Alex Deckmyn

Cited articles

Ally, S., Verstraeten, T., Daems, P.-J., Nowé, A., and Helsen, J.: Modular deep learning approach for wind farm power forecasting and wake loss prediction, Wind Energ. Sci., 10, 779–812, https://doi.org/10.5194/wes-10-779-2025, 2025. a, b
Almeida, L. B.: Multilayer perceptrons, in: Handbook of Neural Computation, pp. C1–2, CRC Press, https://doi.org/10.1201/9780429142772, 2020. a
Barthelmie, R. J., Hansen, K., Frandsen, S. T., Rathmann, O., Schepers, J., Schlez, W., Phillips, J., Rados, K., Zervos, A., Politis, E., et al.: Modelling and measuring flow and wind turbine wakes in large wind farms offshore, Wind Energy: An International Journal for Progress and Applications in Wind Power Conversion Technology, 12, 431–444, 2009. a
BOP: Belgian Offshore Platform website, https://www.belgianoffshoreplatform.be/en/, last access: 2 June 2025. a, b
Borgers, R., van Lipzig, N. P. M., and Meyers, J.: Energy production and inter-farm wake losses in future North Sea wind farms, Environmental Research Letters, https://doi.org/10.1088/1748-9326/add8a2, 2025. a
Download
Short summary
To better predict offshore wind energy in Belgium, we improved the Royal Meteorological Institute (RMI) weather model by directly incorporating the effects of wind turbines. We also used AI to account for wind farm wake effects, where turbines slow down wind for other turbines. By combining physics-based models with a neural network trained on observations from the Belgian Offshore Zone, we achieved more accurate forecasts. This helps ensure a stable power grid and supports the growing role of offshore wind in our energy mix.
Share