A study on the impact of meteorological and emission factors on PM2.5 concentrations based on machine learning
Journal of Environmental Management · 2025-03 · 376 · 124347
DOI: 10.1016/j.jenvman.2025.124347 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Environmental Management, 2025-03. Verfasst von Chenxu Zhao und 12 weiteren Autor:innen. Beteiligte Einrichtung: School of Energy and Environment, Anhui University of Technology, Ma'anshan, 243002, PR China; Guangdong Key Lab of Water & Air Pollution Control, Gu…. Hauptthemen laut MEDLINE: Particulate Matter, Machine Learning, Air Pollutants, Environmental Monitoring. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 103 Literaturangaben. Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
PM2.5 pollution, a major environmental and health concern, is influenced by a complex interplay of emission sources and meteorological conditions. Accurately identifying these factors and their contributions is essential for effective pollution management. This study applies Positive Matrix Factorization (PMF) to identify primary sources of PM2.5 and uses the Light Gradient Boosting Machine (LightGBM) model, SHapley Additive exPlanations (SHAP), and Partial Dependence Plots (PDP) to quantitatively assess the impact of meteorological and emission factors on PM2.5 concentrations. SHAP results reveal that meteorological factors contribute 16.6% (5.3 μg/m3) to PM2.5, with humidity being the most influential, while emission sources account for 83.4% (26.8 μg/m3), with secondary particulate matter being the dominant factor. Secondary particulate matter and biomass burning significantly impacted PM2.5 in the first and fourth quarters, while dust sources became more influential in the second quarter, and coal emissions were most prominent in the second and third quarters. Two-dimensional PDP analysis indicated that in the first and fourth quarters, secondary particulate matter concentration increased with air pressure, and the atmospheric oxidation process was more pronounced under high-humidity conditions during the day. Strong transport conditions, with wind direction shifting from north to east, also influenced secondary particulate matter levels. This study demonstrates that the LightGBM model effectively captures the nonlinear relationships between PM2.5 and meteorological and emission factors, providing a reliable approach for analyzing the causes of PM2.5 pollution.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Energy and Environment, Anhui University of Technology, Ma'anshan, 243002, PR China; Guangdong Key Lab of Water & Air Pollution Control, Guangdong Province Engineering Laboratory for Air Pollution Control, Sou…
- Guangdong Key Lab of Water & Air Pollution Control, Guangdong Province Engineering Laboratory for Air Pollution Control, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou, 5…
- Anqing Ecological Environment Bureau, Anhui Province, Anqing, 246001, PR China.
- Anqing Ecological Environment Monitoring Center, Anhui Province, Anqing, 246001, PR China.
- School of Energy and Environment, Anhui University of Technology, Ma'anshan, 243002, PR China. Electronic address: jiayong2000@163.com.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Zhao, C., Lin, Z., Yang, L., Jiang, M., Qiu, Z., Wang, S., Gu, Y., Ye, W., Pan, Y., Zhang, Y., Wang, T., Jia, Y., & Chen, Z. (2025). A study on the impact of meteorological and emission factors on PM2.5 concentrations based on machine learning. Journal of Environmental Management, 376, 124347. https://doi.org/10.1016/j.jenvman.2025.124347
Vancouver
Zhao C, Lin Z, Yang L, Jiang M, Qiu Z, Wang S, et al. A study on the impact of meteorological and emission factors on PM2.5 concentrations based on machine learning. Journal of Environmental Management. 2025;376:124347. doi:10.1016/j.jenvman.2025.124347
BibTeX
@article{Zhao2025,
author = {Zhao, Chenxu and Lin, Zejian and Yang, Leifeng and Jiang, Mengmeng and Qiu, Zhubing and Wang, Siyu and Gu, Yu and Ye, Wei and Pan, Yusuo and Zhang, Yong and Wang, Tianxin and Jia, Yong and Chen, Zhihang},
title = {A study on the impact of meteorological and emission factors on PM2.5 concentrations based on machine learning},
journal = {Journal of Environmental Management},
year = {2025},
volume = {376},
pages = {124347},
doi = {10.1016/j.jenvman.2025.124347}
}
EUVIMED