Understanding the spatial and seasonal variation of the ground-level ozone in Southeast China with an interpretable machine learning and multi-source remote sensing

Haobin Zhong; Ling Zhen; Qiufang Yao; Yanping Xiao; Jinsong Liu; Baihua Chen; Wei Xu

doi:10.1016/j.scitotenv.2024.170570

Understanding the spatial and seasonal variation of the ground-level ozone in Southeast China with an interpretable machine learning and multi-source remote sensing

Sci Total Environ. 2024 Mar 20:917:170570. doi: 10.1016/j.scitotenv.2024.170570. Epub 2024 Jan 29.

Authors

Haobin Zhong¹, Ling Zhen², Qiufang Yao³, Yanping Xiao³, Jinsong Liu³, Baihua Chen⁴, Wei Xu⁵

Affiliations

¹ School of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, China; Center for Excellence in Regional Atmospheric Environment, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen 361021, China; Jiaxing key Laboratory of Preparation and Application of Advanced Materials for Energy Conservation and Emission Reduction, Jiaxing 314001, China.
² Center for Excellence in Regional Atmospheric Environment, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen 361021, China; Fujian Key Laboratory of Atmospheric Ozone Pollution Prevention, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen 361021, China; University of Chinese Academy of Sciences, Beijing 100049, China.
³ School of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, China; Jiaxing key Laboratory of Preparation and Application of Advanced Materials for Energy Conservation and Emission Reduction, Jiaxing 314001, China.
⁴ Center for Excellence in Regional Atmospheric Environment, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen 361021, China.
⁵ Center for Excellence in Regional Atmospheric Environment, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen 361021, China; Fujian Key Laboratory of Atmospheric Ozone Pollution Prevention, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen 361021, China; University of Chinese Academy of Sciences, Beijing 100049, China. Electronic address: wxu@iue.ac.cn.

PMID: 38296071
DOI: 10.1016/j.scitotenv.2024.170570

Abstract

Ground-level ozone (O₃) pollution poses significant threats to both human health and air quality. This study uses ground observations and satellite retrievals to explore the spatiotemporal characteristics of ground-level O₃ in Zhejiang Province, China. We created data-driven machine learning models that include meteorological, geographical and atmospheric parameters from multi-source remote sensing products, achieving good performance (Pearson's r of 0.81) in explaining regional O₃ dynamics. Analyses revealed the crucial roles of temperature, relative humidity, total column O₃, and the distributions and interactions of precursor (volatile organic compounds and nitrogen oxides) in driving the varied O₃ patterns observed in Zhejiang. Furthermore, the interpretable modeling quantified multifactor interactions that sustain high O₃ levels in spring and autumn, suppress O₃ levels in summer, and inhibit O₃ formation in winter. This work demonstrates the value of a combined approach using satellite and machine learning as an effective novel tool for regional air quality assessment and control.

Keywords: Ground-level ozone; Machine learning; Satellite remote sensing; Spatiotemporal variation.