Data-driven modeling of three-dimensional wind velocity fields in building clusters
Physics of Fluids · 01.07.2026 · 38 (7)
DOI: 10.1063/5.0332748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 14.07.2026. Verfasst von Yue Dong und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Science Foundation, Research Grants Council, University Grants Committee.
Abstract (Originalsprache)
Accurate characterization of urban wind fields is essential for reliable prediction of debris flight and impact on building envelopes. In this study, an efficient data-driven prediction model of wind fields around building clusters is proposed using conditional generative adversarial networks. The input of the prediction model is composed of the building cluster configuration and the inflow wind profile, and the output is the three-dimensional (3D) wind velocity field over the target domain. The training data for this prediction model are generated through computational fluid dynamic simulations and validated through a comprehensive database of wind tunnel measurements. To reduce the computational cost while retaining predictive performance, a sensitivity analysis of input parameters is conducted to inform efficient sampling for data generation. In the proposed framework, the 3D wind field is constructed using the predicted two-dimensional wind field at multiple heights, and the prediction models for the three wind velocity components are trained separately. Windborne debris impact on building envelopes is examined as an illustrative example to demonstrate the applicability of the proposed wind field prediction model.
Förderung
- National Science Foundation
- Research Grants Council, University Grants Committee
Zitieren
APA
Dong, Y., Zhou, S., Guo, Y., Chen, X., & Deng, E. (2026). Data-driven modeling of three-dimensional wind velocity fields in building clusters. Physics of Fluids, 38(7). https://doi.org/10.1063/5.0332748
Vancouver
Dong Y, Zhou S, Guo Y, Chen X, Deng E. Data-driven modeling of three-dimensional wind velocity fields in building clusters. Physics of Fluids. 2026;38(7). doi:10.1063/5.0332748
BibTeX
@article{Dong2026,
author = {Dong, Yue and Zhou, Shangqi and Guo, Yanlin and Chen, Xiuyu and Deng, E},
title = {Data-driven modeling of three-dimensional wind velocity fields in building clusters},
journal = {Physics of Fluids},
year = {2026},
volume = {38},
number = {7},
doi = {10.1063/5.0332748}
}
EUVIMED