Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability

Mai，Zelin1,2; Shen，Huizhong1,2; Zhang，Aoxing1,2; Sun，Haitong Zhe3,4; Zheng，Lianming1,2; Guo，Jianfeng5; Liu，Chanfang5; Chen，Yilin6; Wang，Chen1,2; Ye，Jianhuai1,2; Zhu，Lei1,2; Fu，Tzung May1,2; Yang，Xin1,2; Tao，Shu1,2,7,8

2023

10.1021/acs.est.3c07907

Environmental Science and Technology   影响因子和分区

0013-936X

1520-5851

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 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.

convolutional neural networks deep learning megacity air quality meteorological impact ozone temporal variability surface ozone

SCI

英语

第一 ; 通讯

ENVIRONMENT/ECOLOGY

2-s2.0-85187673369

Scopus

1.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,Shenzhen,518055,China
2.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,518055,China
3.Centre for Atmospheric Science,Yusuf Hamied Department of Chemistry,University of Cambridge,Cambridge,CB2 1EW,United Kingdom
4.Centre for Sustainable Medicine,Yong Loo Lin School of Medicine,National University of Singapore,Singapore,117609,Singapore
5.Shenzhen Ecology and Environment Monitoring Centre of Guangdong Province,Shenzhen,518049,China
6.School of Urban Planning and Design,Peking University,Shenzhen Graduate School,Shenzhen,518055,China
7.College of Urban and Environmental Sciences,Peking University,Beijing,100871,China
8.Institute of Carbon Neutrality,Peking University,Beijing,100871,China

Mai，Zelin,Shen，Huizhong,Zhang，Aoxing,et al. Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability[J]. Environmental Science and Technology,2023.

Mai，Zelin.,Shen，Huizhong.,Zhang，Aoxing.,Sun，Haitong Zhe.,Zheng，Lianming.,...&Tao，Shu.(2023).Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability.Environmental Science and Technology.

Mai，Zelin,et al."Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability".Environmental Science and Technology (2023).