CaltechAUTHORS
  A Caltech Library Service

From COVID-19 to future electrification: Assessing traffic impacts on air quality by a machine-learning model

Yang, Jiani and Wen, Yifan and Wang, Yuan and Zhang, Shaojun and Pinto, Joseph P. and Pennington, Elyse A. and Wang, Zhou and Wu, Ye and Sander, Stanley P. and Jiang, Jonathan H. and Hao, Jiming and Yung, Yuk L. and Seinfeld, John H. (2021) From COVID-19 to future electrification: Assessing traffic impacts on air quality by a machine-learning model. Proceedings of the National Academy of Sciences, 118 (26). Art. No. e2102705118. ISSN 0027-8424. PMCID PMC8256029. doi:10.1073/pnas.2102705118. https://resolver.caltech.edu/CaltechAUTHORS:20210623-180037244

[img] PDF - Published Version
See Usage Policy.

1MB
[img] PDF - Supplemental Material
See Usage Policy.

1MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210623-180037244

Abstract

The large fluctuations in traffic during the COVID-19 pandemic provide an unparalleled opportunity to assess vehicle emission control efficacy. Here we develop a random-forest regression model, based on the large volume of real-time observational data during COVID-19, to predict surface-level NO₂, O₃, and fine particle concentration in the Los Angeles megacity. Our model exhibits high fidelity in reproducing pollutant concentrations in the Los Angeles Basin and identifies major factors controlling each species. During the strictest lockdown period, traffic reduction led to decreases in NO₂ and particulate matter with aerodynamic diameters <2.5 μm by –30.1% and –17.5%, respectively, but a 5.7% increase in O₃. Heavy-duty truck emissions contribute primarily to these variations. Future traffic-emission controls are estimated to impose similar effects as observed during the COVID-19 lockdown, but with smaller magnitude. Vehicular electrification will achieve further alleviation of NO₂ levels.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1073/pnas.2102705118DOIArticle
https://www.pnas.org/content/suppl/2021/06/17/2102705118.DCSupplementalPublisherSupporting Information
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8256029/PubMed CentralArticle
ORCID:
AuthorORCID
Yang, Jiani0000-0003-0037-2413
Wen, Yifan0000-0003-1876-7990
Wang, Yuan0000-0001-6657-8401
Zhang, Shaojun0000-0002-2176-6174
Pinto, Joseph P.0000-0001-5639-8458
Pennington, Elyse A.0000-0003-1736-2342
Wu, Ye0000-0002-9928-1177
Sander, Stanley P.0000-0003-1424-3620
Jiang, Jonathan H.0000-0002-5929-8951
Yung, Yuk L.0000-0002-4263-2562
Seinfeld, John H.0000-0003-1344-4068
Additional Information:© 2021 National Academy of Sciences. Published under the PNAS license. Contributed by John H. Seinfeld, May 3, 2021 (sent for review February 12, 2021; reviewed by Russell R. Dickerson and Alma Hodzic). Y. Wang, S.P.S., J.H.J., and Y.L.Y. acknowledge support by the Jet Propulsion Laboratory, California Institute of Technology, under contract with NASA. E.A.P. and J.H.S. acknowledge support by the Samsung Corporation (award SAMS.2019GRO). S.Z. acknowledges support by the National Key Research and Development Program of China (grant 2017YFC0212100), the National Natural Science Foundation of China (grant 41977180), and Ford Motor Company. J.Y. acknowledges Leo Gallagher and Daniel Kitowski at the California Department of Transportation, Thomas E. Morrell at the Caltech Library, Jin Tao for helpful information on data inputs, and Yu Zhou at Tsinghua University for useful discussions. Data Availability: All study data are included in the article and/or SI Appendix. J.Y. and Y.W. contributed equally to this work. Author contributions: J.Y., Y. Wang, S.Z., and J.H.S. designed research; J.Y., Y. Wen, Y. Wang, and S.Z. performed research; J.Y., Y. Wen, Y. Wang, S.Z., J.P.P., E.A.P., Z.W., Y. Wu, S.P.S., J.H.J., J.H., Y.L.Y., and J.H.S. analyzed data; J.Y., Y. Wen, and S.Z. developed the RF model; and J.Y., Y. Wen, Y. Wang, S.Z., and J.H.S. wrote the paper. Reviewers: R.R.D., University of Maryland, College Park; and A.H., National Center for Atmospheric Research. The authors declare no competing interest. This article contains supporting information online at https://www.pnas.org/lookup/suppl/doi:10.1073/pnas.2102705118/-/DCSupplemental.
Group:COVID-19
Funders:
Funding AgencyGrant Number
NASA/JPL/CaltechUNSPECIFIED
Samsung CorporationSAMS.2019GRO
National Key Research and Development Program of China2017YFC0212100
National Natural Science Foundation of China41977180
Ford Motor CompanyUNSPECIFIED
Subject Keywords:COVID-19; machine learning; air pollution; traffic emissions; vehicular electrification
Issue or Number:26
PubMed Central ID:PMC8256029
DOI:10.1073/pnas.2102705118
Record Number:CaltechAUTHORS:20210623-180037244
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210623-180037244
Official Citation:From COVID-19 to future electrification: Assessing traffic impacts on air quality by a machine-learning model. Jiani Yang, Yifan Wen, Yuan Wang, Shaojun Zhang, Joseph P. Pinto, Elyse A. Pennington, Zhou Wang, Ye Wu, Stanley P. Sander, Jonathan H. Jiang, Jiming Hao, Yuk L. Yung, John H. Seinfeld. Proceedings of the National Academy of Sciences Jun 2021, 118 (26) e2102705118; DOI: 10.1073/pnas.2102705118
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:109562
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:23 Jun 2021 18:15
Last Modified:08 Feb 2022 23:24

Repository Staff Only: item control page