EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Leveraging automated machine learning (AutoML) for urban climate emulation

Junjie Yu, Zhonghua Zheng, Sarah Lindley, Lei Zhao, Chi Wang, Qingyun Wu, Lingcheng Li, David O. Topping, John S. Schreck, David John Gagne, Keith W. Oleson

Big Data and Earth System · 2025

DOI: 10.1016/j.bdes.2025.100040 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Earth System, 2025. Verfasst von Junjie Yu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Amazon Web Services Inc, Microsoft Corporation, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urban climate models are critical for understanding and addressing the impacts of urban climate change. Yet, process-based urban climate models face limitations of high-entry barriers and substantial computing resource consumption, prompting the development of data-driven methods. However, the recently developed urban climate emulators, being location-dependent, are less scalable and may overlook geospatial data. In this study, we develop location-independent machine learning emulators for the daily maximum canyon air temperature. To overcome the complexities associated with model selection and hyperparameter optimization in machine learning, we apply automated machine learning (AutoML) to emulation tasks and propose a feature importance analysis framework for the AutoML models. By comparing four types of global urban climate emulators, we found that the location information and urban surface parameters can improve the emulation performance. The results of the AutoML tasks demonstrate that AutoML excels in learning the physics-based urban climate model, achieving a root mean squared error (RMSE) of 0.81 Kelvin for emulators parameterized with location information and urban surface parameters, and an RMSE of 0.91 Kelvin in the temporal extrapolation scenario. The feature importance of the emulators indicates that urban morphological parameters contribute more to the emulators than radiative and thermal parameters. The study serves as a demonstration of the potential that AutoML holds for advancing urban climate research and facilitating urban climate modeling.

Förderung

  • Amazon Web Services Inc
  • Microsoft Corporation
  • National Science Foundation
  • National Center for Atmospheric Research

Zitieren

APA

Yu, J., Zheng, Z., Lindley, S., Zhao, L., Wang, C., Wu, Q., Li, L., Topping, D. O., Schreck, J. S., Gagne, D. J., & Oleson, K. W. (2025). Leveraging automated machine learning (AutoML) for urban climate emulation. Big Data and Earth System. https://doi.org/10.1016/j.bdes.2025.100040

Vancouver

Yu J, Zheng Z, Lindley S, Zhao L, Wang C, Wu Q, et al. Leveraging automated machine learning (AutoML) for urban climate emulation. Big Data and Earth System. 2025. doi:10.1016/j.bdes.2025.100040

BibTeX
@article{Yu2025,
  author = {Yu, Junjie and Zheng, Zhonghua and Lindley, Sarah and Zhao, Lei and Wang, Chi and Wu, Qingyun and Li, Lingcheng and Topping, David O. and Schreck, John S. and Gagne, David John and Oleson, Keith W.},
  title = {Leveraging automated machine learning (AutoML) for urban climate emulation},
  journal = {Big Data and Earth System},
  year = {2025},
  doi = {10.1016/j.bdes.2025.100040}
}
Kostenlos starten →