Physics-constrained spatiotemporal transformer network: A hybrid paradigm for meteorologically consistent wind speed prediction
Physics of Fluids · 01.05.2026 · 38 (5)
DOI: 10.1063/5.0321414 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 22.05.2026. Verfasst von Lihua Mi und 6 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Gefördert von: A research project of wenzhou university of technology, A project supported by scientific research of zhejiang provincial education department, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate wind speed prediction plays a pivotal role in optimizing wind energy utilization and ensuring stable power grid operations. Despite advancements in data-driven techniques, many existing models generate predictions that deviate from established physical laws, limiting their real-world applicability. To bridge this gap, our study introduces a dual-methodological framework grounded in physics-aware machine learning. To address this, our work introduces two innovations: (a) A physics-informed hybrid architecture combining ConvNeXt-based spatiotemporal attention with a pyramidal transformer, designed to extract features while adhering to fundamental principles such as energy conservation, thermodynamic equations, and buoyancy effects. (b) A constrained optimization framework that enhances predictive accuracy while enforcing meteorological consistency. Evaluations across four seasonal datasets show superior performance over existing methods, with notable gains in both single and multi-step forecasts. For example, in dataset 1, our model attains a mean absolute percentage error of 0.204 (14.3% lower than the next-best approach) and a coefficient of determination (R2) of 0.913 (3.6% higher). Physical constraints further bolster reliability, reducing errors by up to 19.6% (dataset 3) and ensuring compliance with atmospheric physics. Interpretability studies reveal that the model prioritizes physically meaningful variables: 80 m/10 m wind speed ratios dominate predictions, while temperature and humidity contributions vary seasonally.
Förderung
- A research project of wenzhou university of technology
- A project supported by scientific research of zhejiang provincial education department
- National Natural Science Foundation of China
- Basic Research Project of Wenzhou City
Zitieren
APA
Mi, L., Han, Y., Lai, Q., Zhang, X., Chen, H., Liu, J., & Cai, C. S. (2026). Physics-constrained spatiotemporal transformer network: A hybrid paradigm for meteorologically consistent wind speed prediction. Physics of Fluids, 38(5). https://doi.org/10.1063/5.0321414
Vancouver
Mi L, Han Y, Lai Q, Zhang X, Chen H, Liu J, et al. Physics-constrained spatiotemporal transformer network: A hybrid paradigm for meteorologically consistent wind speed prediction. Physics of Fluids. 2026;38(5). doi:10.1063/5.0321414
BibTeX
@article{Mi2026,
author = {Mi, Lihua and Han, Yan and Lai, Qinghui and Zhang, Xin and Chen, Hui and Liu, Jiankun and Cai, C. S.},
title = {Physics-constrained spatiotemporal transformer network: A hybrid paradigm for meteorologically consistent wind speed prediction},
journal = {Physics of Fluids},
year = {2026},
volume = {38},
number = {5},
doi = {10.1063/5.0321414}
}
EUVIMED