A causal machine-learning framework for studying policy impact on air pollution: a case study in COVID-19 lockdowns
American Journal of Epidemiology · 08.01.2025 · 194 (1) · 185-194
DOI: 10.1093/aje/kwae171 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Epidemiology, online erschienen am 03.07.2024. Verfasst von Claire Heffernan und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, United States. Hauptthemen laut MEDLINE: COVID-19, Machine Learning, Air Pollution. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Science Foundation Graduate Research Fellowship Program, NIEHS NIH HHS, US Environmental Protection Agency.
Abstract (Originalsprache)
When studying the impact of policy interventions or natural experiments on air pollution, such as new environmental policies or the opening or closing of an industrial facility, careful statistical analysis is needed to separate causal changes from other confounding factors. Using COVID-19 lockdowns as a case study, we present a comprehensive framework for estimating and validating causal changes from such perturbations. We propose using flexible machine learning–based comparative interrupted time series (CITS) models for estimating such a causal effect. We outline the assumptions required to identify causal effects, showing that many common methods rely on strong assumptions that are relaxed by machine learning models. For empirical validation, we also propose a simple diagnostic criterion, guarding against false effects in baseline years when there was no intervention. The framework is applied to study the impact of COVID-19 lockdowns on atmospheric nitrogen dioxide (NO2) levels in the eastern United States. The machine learning approaches guard against false effects better than common methods and suggest decreases in NO2 levels in 4 US cities (Boston, Massachusetts; New York, New York; Baltimore, Maryland; and Washington, DC) during the pandemic lockdowns. The study showcases the importance of our validation framework in selecting a suitable method and the utility of a machine learning–based CITS model for studying causal changes in air pollution time series. This article is part of a Special Collection on Environmental Epidemiology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, United States.
- Department of Environmental Health and Engineering, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, United States.
- Department of Public Health Sciences, School of Medicine, University of Connecticut, Farmington, CT 06030, United States.
- Department of Chemical and Environmental Engineering, School of Engineering and Applied Science, Yale University, New Haven, CT 06520, United States.
- Department of Statistics and Data Sciences, College of Natural Sciences, University of Texas, Austin, TX 78705, United States.
ORCID-Profile: Claire Heffernan
Förderung
- National Science Foundation Graduate Research Fellowship Program
- NIEHS NIH HHS
- US Environmental Protection Agency
- National Institute of Environmental Health Sciences
Zitieren
APA
Heffernan, C., Koehler, K., Zamora, M. L., Buehler, C., Gentner, D. R., Peng, R. D., & Datta, A. (2025). A causal machine-learning framework for studying policy impact on air pollution: a case study in COVID-19 lockdowns. American Journal of Epidemiology, 194(1), 185-194. https://doi.org/10.1093/aje/kwae171
Vancouver
Heffernan C, Koehler K, Zamora ML, Buehler C, Gentner DR, Peng RD, et al. A causal machine-learning framework for studying policy impact on air pollution: a case study in COVID-19 lockdowns. American Journal of Epidemiology. 2025;194(1):185-194. doi:10.1093/aje/kwae171
BibTeX
@article{Heffernan2025,
author = {Heffernan, Claire and Koehler, Kirsten and Zamora, Misti Levy and Buehler, Colby and Gentner, Drew R and Peng, Roger D and Datta, Abhirup},
title = {A causal machine-learning framework for studying policy impact on air pollution: a case study in COVID-19 lockdowns},
journal = {American Journal of Epidemiology},
year = {2025},
volume = {194},
number = {1},
pages = {185--194},
doi = {10.1093/aje/kwae171}
}
EUVIMED