Evaluation of Model-Based PM 2.5 Estimates for Exposure Assessment during Wildfire Smoke Episodes in the Western U.S.
Environmental Science & Technology · 2023-02-07 · 57 (5) · 2031-2041
DOI: 10.1021/acs.est.2c06288 ↗At a glance
Journal article in Environmental Science & Technology, published online on 2023-01-24. Written by Ellen M Considine and 5 co-authors. Institution: Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts 02115, United States. Major MEDLINE topics: Wildfires, Air Pollution, Air Pollutants. Cited 24 times so far (Crossref); 50 references. The full text is freely available in PubMed Central. Funded by: NIEHS NIH HHS, Harvard University, U.S. Department of Health and Human Services.
Abstract (original language)
Investigating the health impacts of wildfire smoke requires data on people's exposure to fine particulate matter (PM2.5) across space and time. In recent years, it has become common to use machine learning models to fill gaps in monitoring data. However, it remains unclear how well these models are able to capture spikes in PM2.5 during and across wildfire events. Here, we evaluate the accuracy of two sets of high-coverage and high-resolution machine learning-derived PM2.5 data sets created by Di et al. and Reid et al. In general, the Reid estimates are more accurate than the Di estimates when compared to independent validation data from mobile smoke monitors deployed by the US Forest Service. However, both models tend to severely under-predict PM2.5 on high-pollution days. Our findings complement other recent studies calling for increased air pollution monitoring in the western US and support the inclusion of wildfire-specific monitoring observations and predictor variables in model-based estimates of PM2.5. Lastly, we call for more rigorous error quantification of machine-learning derived exposure data sets, with special attention to extreme events.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts 02115, United States.
- Department of Urban and Regional Planning, University of Colorado, Denver, Colorado 80202, United States.
- CU Population Center, University of Colorado, Boulder, Colorado 80309, United States.
- Department of Data Science, Dana-Farber Cancer Institute, Boston, Massachusetts 02215, United States.
- Department of Geography, University of Colorado, Boulder, Colorado 80302, United States.
- Earth Lab, University of Colorado, Boulder, Colorado 80303, United States.
ORCID profiles: Ellen M Considine, Priyanka deSouza
Funding
- NIEHS NIH HHS
- Harvard University
- U.S. Department of Health and Human Services
Cite
APA
Considine, E. M., Hao, J., deSouza, P., Braun, D., Reid, C. E., & Nethery, R. C. (2023). Evaluation of Model-Based PM 2.5 Estimates for Exposure Assessment during Wildfire Smoke Episodes in the Western U.S. Environmental Science & Technology, 57(5), 2031-2041. https://doi.org/10.1021/acs.est.2c06288
Vancouver
Considine EM, Hao J, deSouza P, Braun D, Reid CE, Nethery RC. Evaluation of Model-Based PM 2.5 Estimates for Exposure Assessment during Wildfire Smoke Episodes in the Western U.S. Environmental Science & Technology. 2023;57(5):2031-2041. doi:10.1021/acs.est.2c06288
BibTeX
@article{Considine2023,
author = {Considine, Ellen M and Hao, Jiayuan and deSouza, Priyanka and Braun, Danielle and Reid, Colleen E and Nethery, Rachel C},
title = {Evaluation of Model-Based PM 2.5 Estimates for Exposure Assessment during Wildfire Smoke Episodes in the Western U.S},
journal = {Environmental Science & Technology},
year = {2023},
volume = {57},
number = {5},
pages = {2031--2041},
doi = {10.1021/acs.est.2c06288}
}
EUVIMED