A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm
PLOS One · 2026
DOI: 10.1371/journal.pone.0358271 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Xiaoliang Zhao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Environmental Science and Engineering, Liaoning Technical University, Fuxin, Liaoning, China. Hauptthemen laut MEDLINE: Deep Learning, Particulate Matter, Environmental Monitoring, Air Pollutants. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Liaoning Provincial Department of Education, Liaoning Provincial Education Department, Ordos Science and Technology Research Project.
Abstract (Originalsprache)
Accurate prediction of PM2.5 time series remains challenging. To address this issue, this paper proposes a novel PM2.5 concentration prediction model named FATA-GSPMSTL-CNN-LSTM.Firstly,the optimal feature descriptor set is determined by combining Recursive Feature Elimination with Cross-Validation (RFECV) and Pearson correlation analysis. On the basis of Multiple Seasonal-Trend decomposition using Loess (MSTL), a novel adaptive decomposition algorithm—Grid Search-based Power Spectral MSTL (GSPMSTL)—is constructed by introducing spectral density analysis and grid search strategy, which is adopted to decompose the PM2.5 time series, and the dataset is reconstructed through feature data fusion. The newly developed Fata morgana optimization algorithm (FATA) is utilized to optimize the model hyperparameters for further improving prediction accuracy. Finally, the Convolutional Neural Network- Long Short-Term Memory network (CNN-LSTM) is employed to obtain the final prediction results. Considering climate, topography and seasonal factors, PM2.5 prediction and evaluation are separately conducted in heating seasons and non-heating seasons for Guangzhou and Xianyang cities. The results demonstrate that the proposed model achieves higher prediction accuracy and stability, which can provide important application value for air quality early warning and pollution control.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Environmental Science and Engineering, Liaoning Technical University, Fuxin, Liaoning, China.
- Collaborative Innovation Center of Mine Major Disaster Prevention and Environmental Restoration, Fuxin, Liaoning, China.
- Department of Chemistry, DAV University, Jalandhar, Punjab, India.
- Inner Mongolia Shendong Tianlong Group Co., Ltd., Ordos, Inner Mongolia, China.
- Liaoning Geo-Mineral Investment and Development Group Co., Ltd., Shenyang, Liaoning, China.
- Liaoning Provincial Geology and Mineral Resources Group Mining Co., Ltd., Shenyang, Liaoning, China.
ORCID-Profile: Xiaoliang Zhao
Förderung
- Liaoning Provincial Department of Education
- Liaoning Provincial Education Department
- Ordos Science and Technology Research Project
Zitieren
APA
Zhao, X., Qiao, P., Bharti, B., Li, H., Yang, S., Shi, Q., Qin, Q., & Chen, J. (2026). A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm. PLOS One. https://doi.org/10.1371/journal.pone.0358271
Vancouver
Zhao X, Qiao P, Bharti B, Li H, Yang S, Shi Q, et al. A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm. PLOS One. 2026. doi:10.1371/journal.pone.0358271
BibTeX
@article{Zhao2026,
author = {Zhao, Xiaoliang and Qiao, Pinyuan and Bharti, Bandna and Li, Hanliang and Yang, Shitong and Shi, Qi and Qin, Qiuhong and Chen, Jundian},
title = {A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0358271}
}
EUVIMED