EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GAN Predictability for Urban Environmental Performance: Learnability Mechanisms, Structural Consistency, and Efficiency Bounds

Chenglin Wang, Shiliang Wang, Sixuan Ren, Wenjing Luo, Wenxin Yi, Mei Qing

Atmosphere · 13.12.2025 · 16 (12) · 1403

DOI: 10.3390/atmos16121403 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Atmosphere, online erschienen am 13.12.2025. Verfasst von Chenglin Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative adversarial networks (GANs) can rapidly predict urban environmental performance. However, most existing studies focus on a single target and lack cross-performance comparisons under unified conditions. Under unified urban-form inputs and training settings, this study employs the conditional adversarial model pix2pix to predict four targets—the Universal Thermal Climate Index (UTCI), annual global solar radiation (Rad), sunshine duration (SolarH), and near-surface wind speed (Wind)—and establishes a closed-loop evaluation framework spanning pixel, structural/region-level, cross-task synergy, complexity, and efficiency. The results show that (1) the overall ranking in accuracy and structural consistency is SolarH ≈ Rad > UTCI > Wind; (2) per-epoch times are similar, whereas convergence epochs differ markedly, indicating that total time is primarily governed by convergence difficulty; (3) structurally, Rad/SolarH perform better on hot-region overlap and edge alignment, whereas Wind exhibits larger errors at corners and canyons; (4) in terms of learnability, texture variation explains errors far better than edge count; and (5) cross-task synergy is higher in low-value regions than in high-value regions, with Wind clearly decoupled from the other targets. The distinctive contribution lies in a unified, reproducible evaluation framework, together with learnability mechanisms and applicability bounds, providing fast and reliable evidence for performance-oriented planning and design.

Zitieren

APA

Wang, C., Wang, S., Ren, S., Luo, W., Yi, W., & Qing, M. (2025). GAN Predictability for Urban Environmental Performance: Learnability Mechanisms, Structural Consistency, and Efficiency Bounds. Atmosphere, 16(12), 1403. https://doi.org/10.3390/atmos16121403

Vancouver

Wang C, Wang S, Ren S, Luo W, Yi W, Qing M. GAN Predictability for Urban Environmental Performance: Learnability Mechanisms, Structural Consistency, and Efficiency Bounds. Atmosphere. 2025;16(12):1403. doi:10.3390/atmos16121403

BibTeX
@article{Wang2025,
  author = {Wang, Chenglin and Wang, Shiliang and Ren, Sixuan and Luo, Wenjing and Yi, Wenxin and Qing, Mei},
  title = {GAN Predictability for Urban Environmental Performance: Learnability Mechanisms, Structural Consistency, and Efficiency Bounds},
  journal = {Atmosphere},
  year = {2025},
  volume = {16},
  number = {12},
  pages = {1403},
  doi = {10.3390/atmos16121403}
}
Kostenlos starten →