A comprehensive study of the COVID-19 impact on PM2.5 levels over the contiguous United States: A deep learning approach

Masoud Ghahremanloo; Yannic Lops; Yunsoo Choi; Jia Jung; Seyedali Mousavinezhad; Davyda Hammond

doi:10.1016/j.atmosenv.2022.118944

A comprehensive study of the COVID-19 impact on PM_2.5 levels over the contiguous United States: A deep learning approach

Atmos Environ (1994). 2022 Mar 1:272:118944. doi: 10.1016/j.atmosenv.2022.118944. Epub 2022 Jan 14.

Authors

Masoud Ghahremanloo¹, Yannic Lops¹, Yunsoo Choi¹, Jia Jung¹, Seyedali Mousavinezhad¹, Davyda Hammond²

Affiliations

¹ Department of Earth and Atmospheric Sciences, University of Houston, Houston, TX, 77004, USA.
² Oak Ridge Associated Universities, Oak Ridge, TN, 37830, USA.

Abstract

We investigate the impact of the COVID-19 outbreak on PM_2.5 levels in eleven urban environments across the United States: Washington DC, New York, Boston, Chicago, Los Angeles, Houston, Dallas, Philadelphia, Detroit, Phoenix, and Seattle. We estimate daily PM_2.5 levels over the contiguous U.S. in March-May 2019 and 2020, and leveraging a deep convolutional neural network, we find a correlation coefficient, an index of agreement, a mean absolute bias, and a root mean square error of 0.90 (0.90), 0.95 (0.95), 1.34 (1.24) μg/m³, and 2.04 (1.87) μg/m³, respectively. Results from Google Community Mobility Reports and estimated PM_2.5 concentrations show a greater reduction of PM_2.5 in regions with larger decreases in human mobility and those in which individuals remain in their residential areas longer. The relationship between vehicular PM_2.5 (i.e., the ratio of vehicular PM_2.5 to other sources of PM_2.5) emissions and PM_2.5 reductions (R = 0.77) in various regions indicates that regions with higher emissions of vehicular PM_2.5 generally experience greater decreases in PM_2.5. While most of the urban environments ⸺ Washington DC, New York, Boston, Chicago, Los Angeles, Houston, Dallas, Philadelphia, Detroit, and Seattle ⸺ show a decrease in PM_2.5 levels by 21.1%, 20.7%, 18.5%, 8.05%, 3.29%, 3.63%, 6.71%, 4.82%, 13.5%, and 7.73%, respectively, between March-May of 2020 and 2019, Phoenix shows a 5.5% increase during the same period. Similar to their PM_2.5 reductions, Washington DC, New York, and Boston, compared to other cities, exhibit the highest reductions in human mobility and the highest vehicular PM_2.5 emissions, highlighting the great impact of human activity on PM_2.5 changes in eleven regions. Moreover, compared to changes in meteorological factors, changes in pollutant concentrations, including those of black carbon, organic carbon, SO₂, SO₄, and especially NO₂, appear to have had a significantly greater impact on PM_2.5 changes during the study period.

Keywords: COVID-19; Community multiscale air quality (CMAQ) model; Deep convolutional neural network; Google mobility reports; PM2.5 estimation; United States.