Convolutional versus graph-based surrogate models for inter-farm wake prediction using multi-fidelity transfer learning
Open Access
- 11 August 2026
- journal article
- research article
- Published by Copernicus GmbH in Wind Energy Science
- Vol. 11 (8) , 2869-2893
Abstract
Accurate prediction of wind farm wake interactions is important for energy yield assessment, as offshore wind farms increasingly operate in close proximity to one another. This work presents a systematic comparison of two neural network surrogate models for inter-farm wake deficit prediction: a convolutional neural network (CNN)-based attention residual U-Net (ARU-Net) and a graph neural network (GNN)-based graph neural operator (GNO). Both architectures are trained using multi-fidelity transfer learning, pre-training with low-fidelity engineering model simulations, and then fine-tuning with high-fidelity Reynolds-averaged Navier–Stokes actuator wind farm (RANS-AWF) data. The models are evaluated on procedurally generated wind farm layouts spanning diverse farm sizes, turbine spacings, wind speeds, and ambient turbulence intensities. Both architectures achieve high prediction accuracy but exhibit complementary strengths: evaluated over the wake region (δw≥10-3 m s −1 ) and averaged across both evaluation grids, the GNO achieves a lower root mean squared error (RMSE) (0.024 vs. 0.028 m s −1 ), while the ARU-Net attains a higher F 1 score (0.98 vs. 0.91), reflecting its superior wake boundary capture. Transfer learning substantially benefits the ARU-Net, while the GNO shows a smaller but measurable improvement, achieving its best performance with transfer learning.Keywords
All Related Versions
This publication has 51 references indexed in Scilit:
- Multivariate modeling on wake-affected wind farms by two-stage hybrid graph neural networkApplied Energy, 2025
- Physics-informed deep convolutional hierarchical encoder-decoder neural network for flow field prediction in wind farmsEnergy and AI, 2025
- Learning to optimise wind farms with graph transformersApplied Energy, 2024
- End-to-end wind turbine wake modelling with deep graph representation learningApplied Energy, 2023
- Multi-fidelity modeling of wind farm wakes based on a novel super-fidelity networkEnergy Conversion and Management, 2022
- Diurnal impact of atmospheric stability on inter-farm wake and power generation efficiency at neighboring onshore wind farms in complex terrainEnergy Conversion and Management, 2022
- Physics-induced graph neural network: An application to wind-farm power estimationEnergy, 2019
- Wind-Turbine and Wind-Farm Flows: A ReviewBoundary-Layer Meteorology, 2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Thek-ε-fPmodel applied to double wind turbine wakes using different actuator disk force methodsWind Energy, 2014