View in EDS

Evaluating Chemical Transport and Machine Learning Models for Wildfire Smoke PM 2.5 : Implications for Assessment of Health Impacts.

Saved in:
Bibliographic Details
Title: Evaluating Chemical Transport and Machine Learning Models for Wildfire Smoke PM 2.5 : Implications for Assessment of Health Impacts.
Authors: Qiu M; School of Marine and Atmospheric Sciences, Stony Brook University, Stony Brook, New York 11794, United States.; Program in Public Health, Stony Brook University, Stony Brook, New York 11794, United States.; Doerr School of Sustainability, Stanford University, Stanford, California 94305, United States.; Center for Innovation in Global Health, Stanford University, Stanford, California 94305, United States., Kelp M; Doerr School of Sustainability, Stanford University, Stanford, California 94305, United States., Heft-Neal S; Center on Food Security and the Environment, Stanford University, Stanford, California 94305, United States., Jin X; Department of Environmental Sciences, Rutgers University, New Brunswick, New Jersey 08901, United States., Gould CF; School of Public Health, University of California San Diego, La Jolla, California 92093, United States., Tong DQ; Department of Atmospheric, Oceanic and Earth Sciences, George Mason University, Fairfax, Virginia 22030, United States., Burke M; Doerr School of Sustainability, Stanford University, Stanford, California 94305, United States.; Center on Food Security and the Environment, Stanford University, Stanford, California 94305, United States.; National Bureau of Economic Research, Cambridge, Massachusetts 02139, United States.
Source: Environmental science & technology [Environ Sci Technol] 2024 Dec 31; Vol. 58 (52), pp. 22880-22893. Date of Electronic Publication: 2024 Dec 18.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: American Chemical Society Country of Publication: United States NLM ID: 0213155 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1520-5851 (Electronic) Linking ISSN: 0013936X NLM ISO Abbreviation: Environ Sci Technol Subsets: MEDLINE
Imprint Name(s): Publication: Washington DC : American Chemical Society
Original Publication: Easton, Pa. : American Chemical Society, c1967-
MeSH Terms: Wildfires* , Machine Learning* , Particulate Matter* , Smoke*, Humans ; United States ; Air Pollutants ; Environmental Monitoring
Abstract: Growing wildfire smoke represents a substantial threat to air quality and human health. However, the impact of wildfire smoke on human health remains imprecisely understood due to uncertainties in both the measurement of exposure of population to wildfire smoke and dose-response functions linking exposure to health. Here, we compare daily wildfire smoke-related surface fine particulate matter (PM 2.5 ) concentrations estimated using three approaches, including two chemical transport models (CTMs): GEOS-Chem and the Community Multiscale Air Quality (CMAQ) and one machine learning (ML) model over the contiguous US in 2020, a historically active fire year. In the western US, compared against surface PM 2.5 measurements from the US Environmental Protection Agency (EPA) and PurpleAir sensors, we find that CTMs overestimate PM 2.5 concentrations during extreme smoke episodes by up to 3-5 fold, while ML estimates are largely consistent with surface measurements. However, in the eastern US, where smoke levels were much lower in 2020, CTMs show modestly better agreement with surface measurements. We develop a calibration framework that integrates CTM- and ML-based approaches to yield estimates of smoke PM 2.5 concentrations that outperform individual approach. When combining the estimated smoke PM 2.5 concentrations with county-level mortality rates, we find consistent effects of low-level smoke on mortality but large discrepancies in effects of high-level smoke exposure across different methods. Our research highlights the differences across estimation methods for understanding the health impacts of wildfire smoke and demonstrates the importance of bench-marking estimates with available surface measurements.
Contributed Indexing: Keywords: PM2.5; air quality; chemical transport model; environmental health; machine learning; smoke pollution; wildfire
Substance Nomenclature: 0 (Particulate Matter)
0 (Smoke)
0 (Air Pollutants)
Entry Date(s): Date Created: 20241218 Date Completed: 20250428 Latest Revision: 20250428
Update Code: 20250429
DOI: 10.1021/acs.est.4c05922
PMID: 39694472
Database: MEDLINE
Description
Abstract:Growing wildfire smoke represents a substantial threat to air quality and human health. However, the impact of wildfire smoke on human health remains imprecisely understood due to uncertainties in both the measurement of exposure of population to wildfire smoke and dose-response functions linking exposure to health. Here, we compare daily wildfire smoke-related surface fine particulate matter (PM <subscript>2.5</subscript> ) concentrations estimated using three approaches, including two chemical transport models (CTMs): GEOS-Chem and the Community Multiscale Air Quality (CMAQ) and one machine learning (ML) model over the contiguous US in 2020, a historically active fire year. In the western US, compared against surface PM <subscript>2.5</subscript> measurements from the US Environmental Protection Agency (EPA) and PurpleAir sensors, we find that CTMs overestimate PM <subscript>2.5</subscript> concentrations during extreme smoke episodes by up to 3-5 fold, while ML estimates are largely consistent with surface measurements. However, in the eastern US, where smoke levels were much lower in 2020, CTMs show modestly better agreement with surface measurements. We develop a calibration framework that integrates CTM- and ML-based approaches to yield estimates of smoke PM <subscript>2.5</subscript> concentrations that outperform individual approach. When combining the estimated smoke PM <subscript>2.5</subscript> concentrations with county-level mortality rates, we find consistent effects of low-level smoke on mortality but large discrepancies in effects of high-level smoke exposure across different methods. Our research highlights the differences across estimation methods for understanding the health impacts of wildfire smoke and demonstrates the importance of bench-marking estimates with available surface measurements.
ISSN:1520-5851
DOI:10.1021/acs.est.4c05922