Regional PM2.5 pollution forecasting using a hybrid model based on multi-scales feature fusion and deep learning algorithms
PLOS One · 2025
DOI: 10.1371/journal.pone.0333489 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Yong Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and Statistics, Jishou University, Jishou, China. Hauptthemen laut MEDLINE: Particulate Matter, Deep Learning, Air Pollution, Environmental Monitoring. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The issue of regional haze pollution has become increasingly prominent. However, early warning models for regional haze pollution are significantly lacking. To accurately predict regional PM 2.5 pollution, hourly average concentration data of pollutants from January 1, 2021, to December 31, 2023 in the Chengdu-Chongqing urban agglomeration, along with concurrent surface meteorological data, are used and builds multi-scales feature fusion regional pollution prediction network (MSFRPM) based on a multi-input-multi-output deep learning framework. This model can simultaneously forecast PM 2.5 concentrations for all cities in the region. The results show that the annual and seasonal prediction evaluation metrics of the MSFRPM model are significantly better than those of the baseline models. This can be attributed to the ability of the MSFRPM model to effectively capture the temporal dependency of historical PM 2.5 , the complex nonlinear relationships between other pollutants and meteorological factors within cities, and the multi-scales spatiotemporal dependencies of PM 2.5 transport between cities in the urban agglomeration. In 2023, the Chengdu-Chongqing urban agglomeration experienced 15 days of mild regional pollution, 21 days of moderate pollution, and 2 days of severe pollution, with moderate pollution being the dominant type of PM 2.5 pollution. Seasonally, regional PM 2.5 pollution in the Chengdu-Chongqing urban agglomeration is mainly concentrated in the winter. The MSFRPM model assesses that the interannual and seasonal assessments of regional PM 2.5 pollution in the Chengdu-Chongqing urban agglomeration in 2023 are generally consistent with actual observations. Accurate prediction of regional PM 2.5 pollution is of great significance for the coordinated management and early warning of regional pollution.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- College of Mathematics and Statistics, Jishou University, Jishou, China.
- School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, China.
- School of Rehabilitation Medicine and Health, Hunan University of Medicine, Huaihua, China.
ORCID-Profile: Bo Wu
Zitieren
APA
Zhang, Y., Zhang, W., Wu, B., & Yi, W. (2025). Regional PM2.5 pollution forecasting using a hybrid model based on multi-scales feature fusion and deep learning algorithms. PLOS One. https://doi.org/10.1371/journal.pone.0333489
Vancouver
Zhang Y, Zhang W, Wu B, Yi W. Regional PM2.5 pollution forecasting using a hybrid model based on multi-scales feature fusion and deep learning algorithms. PLOS One. 2025. doi:10.1371/journal.pone.0333489
BibTeX
@article{Zhang2025,
author = {Zhang, Yong and Zhang, Wenya and Wu, Bo and Yi, Weichen},
title = {Regional PM2.5 pollution forecasting using a hybrid model based on multi-scales feature fusion and deep learning algorithms},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0333489}
}
EUVIMED