Bridging sparse air-quality monitoring: machine-learning sharpens daily PM2.5 in 12 cities across two regions
Environmental Monitoring and Assessment · 17.06.2026 · 198 (7)
DOI: 10.1007/s10661-026-15531-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Monitoring and Assessment, online erschienen am 17.06.2026. Verfasst von Negin Rezaei Nokandeh und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Atmospheric and Oceanic Sciences, McGill University, Montréal, QC, H3A 0G4, Canada. Hauptthemen laut MEDLINE: Environmental Monitoring, Particulate Matter, Machine Learning, Air Pollutants. Die Arbeit nennt 42 Literaturangaben.
Abstract (Originalsprache)
Airborne particles smaller than 2.5 µm (PM2.5) pose significant risks to human health and influence the climate. However, the accuracy of ground- and satellite-based estimates varies widely across regions. To evaluate the potential of machine learning (ML) to improve ground PM2.5 concentration measurements, we analyzed ground-level PM2.5 concentrations in 12 cities across the Greater Middle East (GME) and Canada. We deployed three ML models to enhance daily PM2.5 estimations, using nearly a decade of combined ground-based observations and MODIS-MAIAC aerosol optical depth (AOD), along with a uniform predictor set comprising AOD and meteorological variables. To ensure comparability, each city was anchored to a single regulatory monitor in both Canada and the GME. Using tenfold cross-validation, ML improved the AOD–PM2.5 correlation from approximately 0.15 to a mean R of 0.59 in Canada and ~ 0.48 in the GME. A pooled regional model integrating all GME observations achieved high out-of-sample agreement (r ≈ 0.90), compared to an AOD-only fit (r ≈ 0.11). SHAP diagnostics revealed that PM2.5 history (lags and rolling means), AOD, its interaction with physical processes (e.g., temperature and pressure), and boundary-layer height were the dominant drivers in the GME, with more stable influences observed in Canada. PM2.5 levels in Canada rarely exceeded the WHO guideline, whereas exceedances were frequent across all GME cities. These findings demonstrate that ML, particularly when incorporating temporal context and regional pooling, can significantly enhance PM2.5 inference in data-scarce environments. Nonetheless, we emphasize the ongoing need for denser ground monitoring to support high-resolution mapping.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Atmospheric and Oceanic Sciences, McGill University, Montréal, QC, H3A 0G4, Canada.
- Department of Atmospheric and Oceanic Sciences, McGill University, Montréal, QC, H3A 0G4, Canada. parisa.ariya@mcgill.ca.
- Department of Chemistry, McGill University, Montréal, QC, H3A 0G4, Canada. parisa.ariya@mcgill.ca.
Zitieren
APA
Rezaei Nokandeh, N., & Ariya, P. A. (2026). Bridging sparse air-quality monitoring: machine-learning sharpens daily PM2.5 in 12 cities across two regions. Environmental Monitoring and Assessment, 198(7). https://doi.org/10.1007/s10661-026-15531-7
Vancouver
Rezaei Nokandeh N, Ariya PA. Bridging sparse air-quality monitoring: machine-learning sharpens daily PM2.5 in 12 cities across two regions. Environmental Monitoring and Assessment. 2026;198(7). doi:10.1007/s10661-026-15531-7
BibTeX
@article{RezaeiNokandeh2026,
author = {Rezaei Nokandeh, Negin and Ariya, Parisa A},
title = {Bridging sparse air-quality monitoring: machine-learning sharpens daily PM2.5 in 12 cities across two regions},
journal = {Environmental Monitoring and Assessment},
year = {2026},
volume = {198},
number = {7},
doi = {10.1007/s10661-026-15531-7}
}
EUVIMED