Evaluating the real changes of air quality due to clean air actions using a machine learning technique: Results from 12 Chinese mega-cities during 2013-2020

Yong Guo; Kangwei Li; Bin Zhao; Jiandong Shen; William J Bloss; Merched Azzi; Yinping Zhang

doi:10.1016/j.chemosphere.2022.134608

Evaluating the real changes of air quality due to clean air actions using a machine learning technique: Results from 12 Chinese mega-cities during 2013-2020

Chemosphere. 2022 Aug:300:134608. doi: 10.1016/j.chemosphere.2022.134608. Epub 2022 Apr 14.

Authors

Yong Guo¹, Kangwei Li², Bin Zhao³, Jiandong Shen⁴, William J Bloss⁵, Merched Azzi⁶, Yinping Zhang¹

Affiliations

¹ Department of Building Science, Tsinghua University, Beijing, China; Beijing Key Laboratory of Indoor Air Quality Evaluation and Control, Beijing, China.
² Univ Lyon, Université Claude Bernard Lyon 1, CNRS, IRCELYON, F-69626, Villeurbanne, France. Electronic address: likangweizju@foxmail.com.
³ School of Environment, State Key Joint Laboratory of Environment Simulation and Pollution Control, Tsinghua University, Beijing, 100084, China.
⁴ Hangzhou Environmental Monitoring Center Station, Hangzhou, 310007, China.
⁵ School of Geography, Earth and Environmental Sciences, University of Birmingham, Birmingham, United Kingdom.
⁶ New South Wales Department of Planning, Industry and Environment, PO Box 29, Lidcombe, NSW, 1825, Australia.

PMID: 35430204
DOI: 10.1016/j.chemosphere.2022.134608

Abstract

China has implemented two national clean air actions in 2013-2017 and 2018-2020, respectively, with the aim of reducing primary emissions and hence improving air quality at a national level. It is important to examine the effectiveness of such emission reductions and assess the resulting changes in air quality. However, such evaluation is difficult as meteorological factors can amplify, or obscure the changes of air pollutants, in addition to the emission reduction. In this study, we applied the random forest machine learning technique to decouple meteorological influences from emissions changes, and examined the deweathered trends of air pollutants in 12 Chinese mega-cities during 2013-2020. The observed concentrations of all criteria pollutants except O₃ showed significant declines from 2013 to 2020, with PM_2.5 annual decline rates of 6-9% in most cities. In contrast, O₃ concentrations increased with annual growth rates of 1-9%. Compared with the observed results, all the pollutants showed smoothed but similar variation in trend and annual rate-of-change after weather normalization. The response of O₃ to NO₂ concentrations indicated significant regional differences in photochemical regimes, and the differences between observed and deweathered results provided implications for volatile organic compound emission reductions in O₃ pollution mitigation. We further evaluated the effectiveness of first and second clean air actions by removing the meteorological influence. We found that the meteorology can make negative or positive contribution in reducing pollutant concentrations from emission reduction, depending on type of pollutants, locations, and time period. Among the 12 mega-cities, only Beijing showed a positive meteorological contribution in amplifying reductions in main pollutants except O₃ during both clean air action periods. Considering the large and variable impact of meteorological effects in changing air quality, we suggest that similar deweathered analysis is needed as a routine policy evaluation tool on a regional basis.

Keywords: Air quality; Clean air action; Meteorological influence; Random forest model; Weather normalization.

MeSH terms

Air Pollutants* / analysis
Air Pollution* / analysis
China
Cities
Environmental Monitoring / methods
Machine Learning
Particulate Matter / analysis

Substances

Air Pollutants
Particulate Matter