Research on the influencing factors of PM2.5 in China at different spatial scales based on machine learning algorithm
Environment International · 2025-06 · 200 · 109536
DOI: 10.1016/j.envint.2025.109536 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environment International, 2025-06. Verfasst von Meiru Chen und 10 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Atmospheric Environment and Pollution Control, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100…. Hauptthemen laut MEDLINE: Particulate Matter, Machine Learning, Air Pollutants, Environmental Monitoring. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Chinese Academy of Sciences Youth Innovation Promotion Association, National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
PM2.5 pollution is one of the prominent environmental issues currently faced in China, influenced by various factors and showed significant spatial differences. In this study, the Light Gradient Boosting Machine (LightGBM) model was employed in combination with SHapley Additive exPlanation (SHAP) methods to explore the key impact factors (precursor emissions, meteorological conditions, geographical features and socioeconomic factors) on average annual PM2.5 levels from 2015 to 2022 at both city and grid levels in China. The results show that incorporating pollutant concentration into the model enhances its performance, with R2 improving significantly from 0.79 to 0.93, which underscores the importance of pollutant concentration and the outstanding predictive performance of the LightGBM algorithm. Further, after increasing the spatial resolution and applying a grid-level model, R2 further improves to 0.96 ∼ 0.99. SHAP analysis revealed that PM2.5 levels in urban areas are significantly influenced by pollutant concentration such as NO2, CO, and SO2, accounting for 49.3 % of the total impact. In contrast, the grid-based model highlights the dominant role of meteorological factors such as temperature and precipitation influencing PM2.5 levels in non-urban areas. Moreover, the model results also suggested that the PM2.5 pollution in Yangtze River Delta (YRD) and Pearl River Delta (PRD) are mainly controlled by primary emissions, while in Beijing-Tianjin-Hebei (BTH), Fenwei Plain (FWP) and Sichuan Basin (SCB), atmospheric oxidation capacity is a limiting factor. This study underscores the potential of machine learning in atmospheric pollution control and offers insights for developing more effective and region-specific PM2.5 control policies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Laboratory of Atmospheric Environment and Pollution Control, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100085, China; University of Chinese Academy of Sciences, Beijing 100049,…
- Shenyang Academy of Environmental Sciences, Shenyang 110067, China.
Förderung
- Chinese Academy of Sciences Youth Innovation Promotion Association
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Chen, M., Liu, J., Chu, B., Zhao, D., Li, R., Chen, T., Ma, Q., Wang, Y., Zhang, P., Li, H., & He, H. (2025). Research on the influencing factors of PM2.5 in China at different spatial scales based on machine learning algorithm. Environment International, 200, 109536. https://doi.org/10.1016/j.envint.2025.109536
Vancouver
Chen M, Liu J, Chu B, Zhao D, Li R, Chen T, et al. Research on the influencing factors of PM2.5 in China at different spatial scales based on machine learning algorithm. Environment International. 2025;200:109536. doi:10.1016/j.envint.2025.109536
BibTeX
@article{Chen2025,
author = {Chen, Meiru and Liu, Jun and Chu, Biwu and Zhao, Di and Li, Ruiyu and Chen, Tianzeng and Ma, Qingxin and Wang, Yonghong and Zhang, Peng and Li, Hao and He, Hong},
title = {Research on the influencing factors of PM2.5 in China at different spatial scales based on machine learning algorithm},
journal = {Environment International},
year = {2025},
volume = {200},
pages = {109536},
doi = {10.1016/j.envint.2025.109536}
}
EUVIMED