EUVIMEDEUVIMED entdecken
Crossref

Revealing the sources of water-soluble PM2.5 oxidative potential with explainable machine learning

Ling-Yun Zhang, Jing Chen, Qing Yu, Yue-Wei Sun, Ke Xin, Wei-Hua Qin, Mushtaq Ahmad, Shi-Ting Zhai

Environmental Pollution · 2025-12 · 386 · 127278

DOI: 10.1016/j.envpol.2025.127278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Pollution, 2025-12. Verfasst von Ling-Yun Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Joint Laboratory of Environment Simulation and Pollution Control, School of Environment, Beijing Normal University, Beijing, 100875, China;…. Hauptthemen laut MEDLINE: Particulate Matter, Air Pollutants, Environmental Monitoring, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A critical methodological gap persists in quantifying the individual contributions of organic compounds and transition metals to PM2.5 oxidative potential (OP), as their redox coupling fundamentally undermine conventional regression approaches. This study developed an Extreme Gradient Boosting coupled with SHapley Additive exPlanations (XGBoost-SHAP) model, and investigated the key redox-active components and sources of the OP of water-soluble PM2.5 in Beijing, based on dual-assay OP data including both DTT consumption and ·OH production. The dataset included 20 chemical features, 5 meteorological features, and 9 water-soluble organic compounds (WSOC) source features resolved by Positive Matrix Factorization (PMF). Among the analyzed chemical species, moderately hydrophilic WSOC emerged as the most influential factor for both DTT activity (DTTv) and ·OH radical generation (OHv). Moreover, while both primary and secondary WSOC sources contributed significantly to DTTv, with respective contributions of 44.9 % and 55.1 %, secondary WSOC dominated OHv, accounting for 84.6 % of its activity. Besides, simpler WSOC source factors demonstrated enhanced performance in summer simulations compared to the more comprehensive dataset including multiple chemical and meteorological features. By establishing a robust and reliable nonlinear regression approach, this study provides valuable insights into understanding the sources of water-soluble PM2.5 oxidative potential and informs targeted strategies for mitigating the associated health risks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Particulate MatterAir PollutantsEnvironmental MonitoringMachine LearningOxidation-ReductionBeijingSolubilityBoosting Machine Learning AlgorithmsAir Pollution

Stichwörter der Autor:innen

DTT assayOrganic aerosolSHAPSource apportionmentXGBoost

Substanzen

Particulate MatterAir Pollutants

Autor:innen und Institutionen

  • State Key Joint Laboratory of Environment Simulation and Pollution Control, School of Environment, Beijing Normal University, Beijing, 100875, China; Center for Atmospheric Environmental Studies, Beijing Normal Universi…
  • State Key Joint Laboratory of Environment Simulation and Pollution Control, School of Environment, Beijing Normal University, Beijing, 100875, China; CCCC Highway Consultants Co., Ltd., Beijing, 100010, China.
  • State Key Joint Laboratory of Environment Simulation and Pollution Control, School of Environment, Beijing Normal University, Beijing, 100875, China; National Astronomical Research Institute of Thailand, Chiang Mai, 501…

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Zhang, L. Y., Chen, J., Yu, Q., Sun, Y. W., Xin, K., Qin, W. H., Ahmad, M., & Zhai, S. T. (2025). Revealing the sources of water-soluble PM2.5 oxidative potential with explainable machine learning. Environmental Pollution, 386, 127278. https://doi.org/10.1016/j.envpol.2025.127278

Vancouver

Zhang LY, Chen J, Yu Q, Sun YW, Xin K, Qin WH, et al. Revealing the sources of water-soluble PM2.5 oxidative potential with explainable machine learning. Environmental Pollution. 2025;386:127278. doi:10.1016/j.envpol.2025.127278

BibTeX
@article{Zhang2025,
  author = {Zhang, Ling-Yun and Chen, Jing and Yu, Qing and Sun, Yue-Wei and Xin, Ke and Qin, Wei-Hua and Ahmad, Mushtaq and Zhai, Shi-Ting},
  title = {Revealing the sources of water-soluble PM2.5 oxidative potential with explainable machine learning},
  journal = {Environmental Pollution},
  year = {2025},
  volume = {386},
  pages = {127278},
  doi = {10.1016/j.envpol.2025.127278}
}
Kostenlos starten →