Pretrained GNN model weights for SCADA data imputation (Kelmarsh and Penmanshiel wind farms)
Abstract
Model weights for GNN Wind Farm models based on Kelmarsh and Penmanshiel wind farm data. This is part of the project Data imputation for SCADA data using Graph Neural Networks and Transfer Learning. The model files (.pt) are PyTorch state dicts. To load the models, the FarmGATv2 class from the code repository (DOI pending) needs to be used.
Fields of Study & Subjects
Advanced Graph Neural Networks
Energy Load and Power Forecasting
Wind Turbine Control Systems
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 30 January 2026
- Document type
- Dataset