Article: Regional wind speed prediction model based on graph attention network and meteorological coupled equations Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.47 pp.71 - 88 Abstract: Aiming at the challenges of spatio-temporal nonlinearity and physical consistency in regional wind speed prediction, this paper proposes graph attention network with physical constraints, a new model that fuses the graph attention network and meteorological equations. The model dynamically captures the complex relationship between meteorological stations through the graph attention mechanism and jointly optimises the loss function with the horizontal momentum equation as the physical constraint. Experiments based on high-resolution data in the Beijing-Tianjin-Hebei region from 2018-2021 show that the root mean square error and mean absolute error of graph attention network with physical constraints in 24-hour forecasts are 1.52 m/s and 1.11 m/s, respectively, which are reduced by 11.1% and 11.9% compared to the optimal baseline, and the R2 is improved to 0.948. Its excellent performance in extreme events provides a new paradigm for high-precision, interpretable weather prediction. Inderscience Publishers - linking academia, business and industry through research

Title: Regional wind speed prediction model based on graph attention network and meteorological coupled equations

Authors: Yuechao Zhang

Addresses: Long Yuan (Beijing) New Energy Engineering Technology Co., Ltd., Beijing, 100034, China

Abstract: Aiming at the challenges of spatio-temporal nonlinearity and physical consistency in regional wind speed prediction, this paper proposes graph attention network with physical constraints, a new model that fuses the graph attention network and meteorological equations. The model dynamically captures the complex relationship between meteorological stations through the graph attention mechanism and jointly optimises the loss function with the horizontal momentum equation as the physical constraint. Experiments based on high-resolution data in the Beijing-Tianjin-Hebei region from 2018-2021 show that the root mean square error and mean absolute error of graph attention network with physical constraints in 24-hour forecasts are 1.52 m/s and 1.11 m/s, respectively, which are reduced by 11.1% and 11.9% compared to the optimal baseline, and the R² is improved to 0.948. Its excellent performance in extreme events provides a new paradigm for high-precision, interpretable weather prediction.

Keywords: wind speed prediction; graph attention networks; physically informed machine learning; coupled meteorological equations; spatio-temporal prediction.

DOI: 10.1504/IJICT.2025.150606

International Journal of Information and Communication Technology, 2025 Vol.26 No.47, pp.71 - 88

Received: 07 Sep 2025
Accepted: 17 Oct 2025
Published online: 17 Dec 2025 *

Title: Regional wind speed prediction model based on graph attention network and meteorological coupled equations

Keep up-to-date