Intelligent Super‐Resolution of Wind Fields: A Terrain‐Aware Approach for 25 km to 1 km Downscaling
Journal of Geophysical Research: Atmospheres · 16.06.2026 · 131 (11)
DOI: 10.1029/2025jd045875 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Geophysical Research: Atmospheres, online erschienen am 01.06.2026. Verfasst von Zilong Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben.
Abstract (Originalsprache)
High‐resolution kilometer‐scale wind fields are essential for wind energy assessment and extreme weather analysis. However, current downscaling methods still have huge biases in complex terrain. In this study, we propose Terrain‐Aware Vision Transformer (TA‐ViT), a novel deep learning framework for wind field downscaling from 25 to 1 km, which integrates dual‐branch patch embedding, feature‐wise linear modulation (FiLM), type‐aware attention gating, and progressive upsampling to effectively capture terrain‐induced wind modifications. The model achieves superior performance with root mean square error of 1.15 m , Pearson correlation coefficient of 0.93, structural similarity index measure of 0.78, and peak signal‐to‐noise ratio (PSNR) of 20.48 dB. Notably, TA‐ViT demonstrates enhanced performance in steep terrain regions, outperforming traditional statistical downscaling method, interpolation method, and deep learning baselines. During typhoon passages, the model demonstrates robustness in capturing localized wind extremes under extreme and historical weather events. These findings suggest that TA‐ViT provides a promising physics‐aware solution for high‐resolution wind field downscaling.
Zitieren
APA
Li, Z., Huang, W., Sun, D., Li, A., Liu, Y., Liu, D., Dong, W., & Chen, D. (2026). Intelligent Super‐Resolution of Wind Fields: A Terrain‐Aware Approach for 25 km to 1 km Downscaling. Journal of Geophysical Research: Atmospheres, 131(11). https://doi.org/10.1029/2025jd045875
Vancouver
Li Z, Huang W, Sun D, Li A, Liu Y, Liu D, et al. Intelligent Super‐Resolution of Wind Fields: A Terrain‐Aware Approach for 25 km to 1 km Downscaling. Journal of Geophysical Research: Atmospheres. 2026;131(11). doi:10.1029/2025jd045875
BibTeX
@article{Li2026,
author = {Li, Zilong and Huang, Wenyu and Sun, Danyi and Li, Aiwei and Liu, Yongqian and Liu, Dongqing and Dong, Wenhao and Chen, Deliang},
title = {Intelligent Super‐Resolution of Wind Fields: A Terrain‐Aware Approach for 25 km to 1 km Downscaling},
journal = {Journal of Geophysical Research: Atmospheres},
year = {2026},
volume = {131},
number = {11},
doi = {10.1029/2025jd045875}
}
EUVIMED