A Residual Learning Framework for ERA5 Offshore Wind Speed Bias Correction and Gap Reconstruction Toward Offshore Wind Energy Applications
Energies · 01.08.2026 · 19 (15) · 3617
DOI: 10.3390/en19153617 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 01.08.2026. Verfasst von Dibo Dong und 6 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major Special Project of Fujian Province.
Abstract (Originalsprache)
Continuous and reliable offshore wind speed time series are essential for offshore wind resource assessment, power forecasting, and long-term wind energy analysis. However, ERA5 reanalysis data may contain site-scale biases over offshore areas, and missing records in offshore wind-tower observations limit their practical use. To improve the reliability of offshore wind speed series, this study proposes a residual learning framework for ERA5 bias correction and continuous gap reconstruction by integrating ERA5 background fields with target- and neighboring-station information. Using FINO1 and FINO3 observations in the North Sea from 2018 to 2025, ERA5 wind-vector components were matched with tower observations, and residuals of the east–west and north–south wind components were used as prediction targets. Statistical methods, linear models, tree-based ensemble models, and GRU models were evaluated under a cross-year framework, with additional analyses of historical residuals, neighboring-station information, and wind-direction-related features. Results show that target-station historical residuals dominate site-scale correction, reducing RMSE by 50.77% and 32.69% for FINO1 and FINO3, respectively, under a 1 h observation lag. Neighboring-station information provides useful constraints when local observations are limited or missing. The framework maintains stable improvements across years and strong-wind conditions and supports reliable offshore wind speed reconstruction for wind energy applications.
Förderung
- Major Special Project of Fujian Province
Zitieren
APA
Dong, D., Nie, L., Zhu, B., Lin, Z., Guo, Q., Wang, S., & Ding, Y. (2026). A Residual Learning Framework for ERA5 Offshore Wind Speed Bias Correction and Gap Reconstruction Toward Offshore Wind Energy Applications. Energies, 19(15), 3617. https://doi.org/10.3390/en19153617
Vancouver
Dong D, Nie L, Zhu B, Lin Z, Guo Q, Wang S, et al. A Residual Learning Framework for ERA5 Offshore Wind Speed Bias Correction and Gap Reconstruction Toward Offshore Wind Energy Applications. Energies. 2026;19(15):3617. doi:10.3390/en19153617
BibTeX
@article{Dong2026,
author = {Dong, Dibo and Nie, Luyi and Zhu, Benlu and Lin, Zexi and Guo, Qiaoying and Wang, Shangwei and Ding, Yiting},
title = {A Residual Learning Framework for ERA5 Offshore Wind Speed Bias Correction and Gap Reconstruction Toward Offshore Wind Energy Applications},
journal = {Energies},
year = {2026},
volume = {19},
number = {15},
pages = {3617},
doi = {10.3390/en19153617}
}
EUVIMED