Domain-informed CNN architectures for downscaling regional wind forecasts
File(s)
Published version
Author(s)
Campbell, Alexander M
Warder, Simon C
Bhaskaran, B
Piggott, Matthew D
Type
Journal Article
Abstract
High-resolution wind speed forecasts are of great importance to the wind energy industry, from short-term energy forecasting and trading to longer-term resource assessment and planning. Generating high-resolution regional wind forecasts currently requires compute-intensive numerical models to downscale from a global forecast. Black-box AI models, once trained, can produce results in a fraction of the time and cost; however, they tend to produce smoothed outputs, are not interpretable and generalise poorly. The domain-informed AI architecture presented in this work seeks to address these problems by incorporating prior static fields directly into the model architecture. Specifically, the proposed approach combines two sequential U-Nets – the first upsamples the input wind fields and expands the number of feature maps, a fusion layer then injects prior static data such as topography, and a second U-Net generates the final output wind field. This approach improves all performance metrics versus a baseline U-Net model and generalises better to out-of-sample scenarios. In addition, this study compares the performance of several loss functions, including standard pixel-wise measures such as mean-squared error, structural similarity and frequency-focused functions, and a function based on Wiener filter theory. All loss functions, with the exception of the Wiener loss, perform comparably and tend to attenuate higher-frequency detail. Although the Wiener loss encourages higher frequencies, it over-estimates amplitudes. A composite Wiener-L1 loss function balances generating high-frequency detail and correctly predicting amplitudes.
Date Issued
2025-05-01
Date Acceptance
2025-02-05
Citation
Energy and AI, 2025, 20
ISSN
2666-5468
Publisher
Elsevier BV
Journal / Book Title
Energy and AI
Volume
20
Copyright Statement
© 2025 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
License URL
Identifier
10.1016/j.egyai.2025.100485
Publication Status
Published
Article Number
100485
Date Publish Online
2025-02-13