EUVIMEDOpdag EUVIMED
Crossref

Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability

Zelin Mai, Huizhong Shen iD, Aoxing Zhang iD, Haitong Zhe Sun iD, Lianming Zheng, Jianfeng Guo, Chanfang Liu, Yilin Chen iD, Chen Wang iD, Jianhuai Ye, Lei Zhu, Tzung-May Fu iD and 2 more

Environmental Science & Technology · 2024-09-03 · 58 (35) · 15691-15701

DOI: 10.1021/acs.est.3c07907 ↗

At a glance

Journal article in Environmental Science & Technology, published online on 2024-03-15. Written by Zelin Mai and 13 co-authors. Institution: Shenzhen Key Laboratory of Precision Measurement and Early Warning Technology for Urban Environmental Health Risks, School of Environmental Science a…. Major MEDLINE topics: Ozone, Neural Networks, Computer. Cited 23 times so far (Crossref); 69 references. Funded by: Guangdong Provincial Department of Science and Technology, Ministry of Science and Technology of the People's Republic of China, Science, Technology and Innovation Commission of Shenzhen Municipality.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Ozone pollution is profoundly modulated by meteorological features such as temperature, air pressure, wind, and humidity. While many studies have developed empirical models to elucidate the effects of meteorology on ozone variability, they predominantly focus on local weather conditions, overlooking the influences from high-altitude and broader regional meteorological patterns. Here, we employ convolutional neural networks (CNNs), a technique typically applied to image recognition, to investigate the influence of three-dimensional spatial variations in meteorological fields on the daily, seasonal, and interannual dynamics of ozone in Shenzhen, a major coastal urban center in China. Our optimized CNNs model, covering a 13° × 13° spatial domain, effectively explains over 70% of daily ozone variability, outperforming alternative empirical approaches by 7 to 62%. Model interpretations reveal the crucial roles of 2-m temperature and humidity as primary drivers, contributing 16% and 15% to daily ozone fluctuations, respectively. Regional wind fields account for up to 40% of ozone changes during the episodes. CNNs successfully replicate observed ozone temporal patterns, attributing -5-6 μg·m-3 of interannual ozone variability to weather anomalies. Our interpretable CNNs framework enables quantitative attribution of historical ozone fluctuations to nonlinear meteorological effects across spatiotemporal scales, offering vital process-based insights for managing megacity air quality amidst changing climate regimes.

Subjects

MeSH terms (MEDLINE)

OzoneNeural Networks, ComputerChinaEnvironmental MonitoringSeasonsWeatherAir Pollutants

Author keywords

convolutional neural networksdeep learningmegacity air qualitymeteorological impactozone temporal variabilitysurface ozone

Substances

OzoneAir Pollutants

Authors and institutions

  • Shenzhen Key Laboratory of Precision Measurement and Early Warning Technology for Urban Environmental Health Risks, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhe…
  • Guangdong Provincial Observation and Research Station for Coastal Atmosphere and Climate of the Greater Bay Area, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen…
  • Centre for Atmospheric Science, Yusuf Hamied Department of Chemistry, University of Cambridge, Cambridge CB2 1EW, U.K.
  • Centre for Sustainable Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117609, Republic of Singapore.
  • Shenzhen Ecology and Environment Monitoring Centre of Guangdong Province, Shenzhen 518049, China.
  • School of Urban Planning and Design, Peking University, Shenzhen Graduate School, Shenzhen 518055, China.

ORCID profiles: Huizhong Shen, Aoxing Zhang, Haitong Zhe Sun, Yilin Chen, Chen Wang, Tzung-May Fu, Xin Yang, Shu Tao

Funding

  • Guangdong Provincial Department of Science and Technology
  • Ministry of Science and Technology of the People's Republic of China
  • Science, Technology and Innovation Commission of Shenzhen Municipality
  • Department of Education of Guangdong Province
  • Southern University of Science and Technology
  • National Natural Science Foundation of China
  • Shenzhen Key Laboratory of Precision Measurement and Early Warning Technology for Urban Environmental Health Risks, Southern University of Science and Technolo…

Cite

APA

Mai, Z., Shen, H., Zhang, A., Sun, H. Z., Zheng, L., Guo, J., Liu, C., Chen, Y., Wang, C., Ye, J., Zhu, L., Fu, T. M., Yang, X., & Tao, S. (2024). Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability. Environmental Science & Technology, 58(35), 15691-15701. https://doi.org/10.1021/acs.est.3c07907

Vancouver

Mai Z, Shen H, Zhang A, Sun HZ, Zheng L, Guo J, et al. Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability. Environmental Science & Technology. 2024;58(35):15691-15701. doi:10.1021/acs.est.3c07907

BibTeX
@article{Mai2024,
  author = {Mai, Zelin and Shen, Huizhong and Zhang, Aoxing and Sun, Haitong Zhe and Zheng, Lianming and Guo, Jianfeng and Liu, Chanfang and Chen, Yilin and Wang, Chen and Ye, Jianhuai and Zhu, Lei and Fu, Tzung-May and Yang, Xin and Tao, Shu},
  title = {Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability},
  journal = {Environmental Science & Technology},
  year = {2024},
  volume = {58},
  number = {35},
  pages = {15691--15701},
  doi = {10.1021/acs.est.3c07907}
}
Start for free →