Satellite Retrieval of Air Pollution Changes in Central and Eastern China during COVID-19 Lockdown Based on a Machine Learning Model

With the implementation of the 2018–2020 Clean Air Action Plan (CAAP) the and impact from COVID-19 lockdowns in 2020, air pollution emissions in central and eastern China have decreased markedly. Here, by combining satellite remote sensing, re-analysis, and ground-based observational data, we established a machine learning (ML) model to analyze annual and seasonal changes in primary air pollutants in 2020 compared to 2018 and 2019 over central and eastern China. The root mean squared errors (RMSE) for the PM2.5, PM10, O3, and CO validation dataset were 9.027 μg/m3, 20.312 μg/m3, 10.436 μg/m3, and 0.097 mg/m3, respectively. The geographical random forest (RF) model demonstrated good performance for four main air pollutants. Notably, PM2.5, PM10, and CO decreased by 44.1%, 43.2%, and 35.9% in February 2020, which was likely influenced by the COVID-19 lockdown and primarily lasted until May 2020. Furthermore, PM2.5, PM10, O3, and CO decreased by 16.4%, 24.2%, 2.7%, and 19.8% in 2020 relative to the average values in 2018 and 2019. Moreover, the reduction in O3 emissions was not universal, with a significant increase (~20–40%) observed in uncontaminated areas.

[1]  A. Stohl,et al.  Rapid decline of carbon monoxide emissions in the Fenwei Plain in China during the three-year Action Plan on defending the blue sky. , 2023, Journal of environmental management.

[2]  A. Salamova,et al.  Temporal environmental hysteresis: A definition and implications for polybrominated diphenyl ethers. , 2021, The Science of the total environment.

[3]  Congbo Song,et al.  Chemistry of Atmospheric Fine Particles During the COVID‐19 Pandemic in a Megacity of Eastern China , 2020, Geophysical research letters.

[4]  Zhanqing Li,et al.  Abnormally Shallow Boundary Layer Associated With Severe Air Pollution During the COVID‐19 Lockdown in China , 2020, Geophysical research letters.

[5]  Z. Ma,et al.  Atmospheric inverse estimates of CO emissions from Zhengzhou, China. , 2020, Environmental pollution.

[6]  J. Veefkind,et al.  NOx Emissions Reduction and Rebound in China Due to the COVID‐19 Crisis , 2020, Geophysical Research Letters.

[7]  X. Yue,et al.  Meteorological influences on PM2.5 and O3 trends and associated health burden since China's clean air actions. , 2020, The Science of the total environment.

[8]  D. Worsnop,et al.  A chemical cocktail during the COVID-19 outbreak in Beijing, China: Insights from six-year aerosol particle composition measurements during the Chinese New Year holiday , 2020, Science of The Total Environment.

[9]  Zhongfeng Qiu,et al.  Air Pollution Scenario over China during COVID-19 , 2020, Remote. Sens..

[10]  S. Griffith,et al.  Long-range air pollution transport in East Asia during the first week of the COVID-19 lockdown in China , 2020, Science of The Total Environment.

[11]  Xuejun Liu,et al.  Puzzling Haze Events in China During the Coronavirus (COVID‐19) Shutdown , 2020, Geophysical research letters.

[12]  Yang Liu,et al.  Spatiotemporal distributions of surface ozone levels in China from 2005 to 2017: A machine learning approach. , 2020, Environment international.

[13]  Ming Zhang,et al.  The influence of multiple environmental regulations on haze pollution: Evidence from China , 2020, Atmospheric Pollution Research.

[14]  J. Veefkind,et al.  Impact of Coronavirus Outbreak on NO2 Pollution Assessed Using TROPOMI and OMI Observations , 2020, Geophysical research letters.

[15]  D. Qin,et al.  PM2.5 and O3 pollution during 2015-2019 over 367 Chinese cities: Spatiotemporal variations, meteorological and topographical impacts. , 2020, Environmental pollution.

[16]  A. Zhang,et al.  Does lockdown reduce air pollution? Evidence from 44 cities in northern China , 2020, Science of The Total Environment.

[17]  S. Davis,et al.  Enhanced secondary pollution offset reduction of primary emissions during COVID-19 lockdown in China , 2020, National science review.

[18]  D. Jacob,et al.  A two-pollutant strategy for improving ozone and particulate air quality in China , 2019, Nature Geoscience.

[19]  Zhanqing Li,et al.  Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach , 2019, Remote Sensing of Environment.

[20]  Qiang Zhang,et al.  Assessing the impact of clean air action on air quality trends in Beijing using a machine learning technique , 2019, Atmospheric Chemistry and Physics.

[21]  Li Li,et al.  Regional differences in spatial spillover and hysteresis effects: A theoretical and empirical study of environmental regulations on haze pollution in China , 2019, Journal of Cleaner Production.

[22]  Jianjun Liu,et al.  Satellite-based PM2.5 estimation directly from reflectance at the top of the atmosphere using a machine learning algorithm , 2019, Atmospheric Environment.

[23]  L. Knibbs,et al.  Spatiotemporal patterns of PM10 concentrations over China during 2005-2016: A satellite-based estimation using the random forests approach. , 2018, Environmental pollution.

[24]  L. Knibbs,et al.  A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information. , 2018, The Science of the total environment.

[25]  Jianjun He,et al.  Air pollution in China: Status and spatiotemporal variations. , 2017, Environmental pollution.

[26]  Yu Zhan,et al.  Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm , 2017 .

[27]  Zachary M. Jones,et al.  edarf: Exploratory Data Analysis using Random Forests , 2016, J. Open Source Softw..

[28]  Hongjun Mao,et al.  The evaluation of emission control to PM concentration during Beijing APEC in 2014 , 2016 .

[29]  Chon-lin Lee,et al.  A new conceptual model for quantifying transboundary contribution of atmospheric pollutants in the East Asian Pacific rim region. , 2016, Environment international.

[30]  Chang‐Hoi Ho,et al.  Influence of transboundary air pollutants from China on the high-PM10 episode in Seoul, Korea for the period October 16–20, 2008 , 2013 .

[31]  H. Tani,et al.  Study on spatial distribution of crop residue burning and PM2.5 change in China. , 2017, Environmental pollution.

[32]  P. Brimblecombe,et al.  Ozone pollution in China: A review of concentrations, meteorological influences, chemical precursors, and effects. , 2017, The Science of the total environment.

[33]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[34]  Fridolin Linder,et al.  Exploratory Data Analysis using Random Forests ∗ , 2015 .