Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems

Yu, Hangyi; Gao, Sheng; Zhao, Hanqing; Zhang, Yu; Lin, Lianlei; Zhang, Zongwei; Wang, Junkai

doi:10.3390/en19122847

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems

by

Hangyi Yu

,

Sheng Gao

,

Hanqing Zhao

,

Yu Zhang

,

Lianlei Lin

^*

,

Zongwei Zhang

and

Junkai Wang

School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China

^*

Author to whom correspondence should be addressed.

Energies 2026, 19(12), 2847; https://doi.org/10.3390/en19122847 (registering DOI)

Submission received: 27 March 2026 / Revised: 20 May 2026 / Accepted: 8 June 2026 / Published: 15 June 2026

(This article belongs to the Special Issue AI-Driven Modeling and Optimization for Industrial Energy Systems)

Download Versions Notes

Abstract

Wind speed prediction is an essential spatiotemporal forecasting task in wind energy systems, yet it remains challenging due to the nonlinear and dynamic characteristics of atmospheric processes. The evolution of wind is governed by physical laws, which can be effectively described using partial differential equations (PDEs). To improve forecasting reliability and accuracy, this paper proposes a novel network model, termed DynWindNet, which integrates equation-based dynamics with data-driven dynamics within a unified framework. Specifically, an interactive dual-branch architecture is designed, where a Physics–Data Coupling Module (PDCM) enables adaptive information exchange between the two dynamics via attention-based gating mechanisms. In addition, a frequency-aware enhancement module (FAEM) is introduced to refine the representations of the data-driven branch by selectively emphasizing informative frequency components. Experimental results on the ERA5 dataset demonstrate that DynWindNet consistently outperforms representative baseline methods across atmospheric pressure levels. Overall, the proposed framework provides an effective approach for integrating physics-guided evolution modeling with deep spatiotemporal representation learning in wind field forecasting.

Keywords: wind speed prediction; spatiotemporal forecasting; physics-informed neural networks; convection–diffusion modeling; hybrid dynamics modeling

Share and Cite

MDPI and ACS Style

Yu, H.; Gao, S.; Zhao, H.; Zhang, Y.; Lin, L.; Zhang, Z.; Wang, J. Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems. Energies 2026, 19, 2847. https://doi.org/10.3390/en19122847

AMA Style

Yu H, Gao S, Zhao H, Zhang Y, Lin L, Zhang Z, Wang J. Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems. Energies. 2026; 19(12):2847. https://doi.org/10.3390/en19122847

Chicago/Turabian Style

Yu, Hangyi, Sheng Gao, Hanqing Zhao, Yu Zhang, Lianlei Lin, Zongwei Zhang, and Junkai Wang. 2026. "Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems" Energies 19, no. 12: 2847. https://doi.org/10.3390/en19122847

APA Style

Yu, H., Gao, S., Zhao, H., Zhang, Y., Lin, L., Zhang, Z., & Wang, J. (2026). Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems. Energies, 19(12), 2847. https://doi.org/10.3390/en19122847

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI