A deep learning-based hybrid method for PM2.5 prediction in central and western China

Abstract To mitigate the adverse effects of air pollution, accurate PM2.5 prediction is particularly important. It is difficult for existing models to escape the limitations attached to a single model itself. This study proposes a hybrid PM2.5 prediction model utilizing deep learning techniques, whi...

Full description

Saved in:
Bibliographic Details
Main Authors: Zuhan Liu, Zihai Fang, Yuanhao Hu
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-95460-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850208343423975424
author Zuhan Liu
Zihai Fang
Yuanhao Hu
author_facet Zuhan Liu
Zihai Fang
Yuanhao Hu
author_sort Zuhan Liu
collection DOAJ
description Abstract To mitigate the adverse effects of air pollution, accurate PM2.5 prediction is particularly important. It is difficult for existing models to escape the limitations attached to a single model itself. This study proposes a hybrid PM2.5 prediction model utilizing deep learning techniques, which aims to complement each other’s strengths through model fusion. The model integrates the transformer and LSTM architectures and employs parameter optimization through the particle swarm optimization (PSO) algorithm. The proposed model achieves superior performance by utilizing the gating mechanism of the LSTM model, the positional encoding and self-attention mechanism of the Transformer model, and PSO’s robust optimization capabilities. Experimental results show that the new model outperforms both the traditional LSTM model and the PSO-LSTM model in the PM2.5 prediction task, and its evaluation metrics, R2, MAE, MBE, RMSE, and MAPE, are all improved. Furthermore, the model demonstrates stable performance across different cities and various periods. This study offers a robust approach to improving the accuracy and reliability of PM2.5 forecasting.
format Article
id doaj-art-e7ba92a585d74e268d7b02105af9d468
institution OA Journals
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e7ba92a585d74e268d7b02105af9d4682025-08-20T02:10:16ZengNature PortfolioScientific Reports2045-23222025-03-0115111710.1038/s41598-025-95460-6A deep learning-based hybrid method for PM2.5 prediction in central and western ChinaZuhan Liu0Zihai Fang1Yuanhao Hu2School of Information Engineering, Nanchang Institute of TechnologySchool of Information Engineering, Nanchang Institute of TechnologySchool of Information Engineering, Nanchang Institute of TechnologyAbstract To mitigate the adverse effects of air pollution, accurate PM2.5 prediction is particularly important. It is difficult for existing models to escape the limitations attached to a single model itself. This study proposes a hybrid PM2.5 prediction model utilizing deep learning techniques, which aims to complement each other’s strengths through model fusion. The model integrates the transformer and LSTM architectures and employs parameter optimization through the particle swarm optimization (PSO) algorithm. The proposed model achieves superior performance by utilizing the gating mechanism of the LSTM model, the positional encoding and self-attention mechanism of the Transformer model, and PSO’s robust optimization capabilities. Experimental results show that the new model outperforms both the traditional LSTM model and the PSO-LSTM model in the PM2.5 prediction task, and its evaluation metrics, R2, MAE, MBE, RMSE, and MAPE, are all improved. Furthermore, the model demonstrates stable performance across different cities and various periods. This study offers a robust approach to improving the accuracy and reliability of PM2.5 forecasting.https://doi.org/10.1038/s41598-025-95460-6Long short-term memory (LSTM)TransformerParticle swarm optimization (PSO)PM2.5 prediction
spellingShingle Zuhan Liu
Zihai Fang
Yuanhao Hu
A deep learning-based hybrid method for PM2.5 prediction in central and western China
Scientific Reports
Long short-term memory (LSTM)
Transformer
Particle swarm optimization (PSO)
PM2.5 prediction
title A deep learning-based hybrid method for PM2.5 prediction in central and western China
title_full A deep learning-based hybrid method for PM2.5 prediction in central and western China
title_fullStr A deep learning-based hybrid method for PM2.5 prediction in central and western China
title_full_unstemmed A deep learning-based hybrid method for PM2.5 prediction in central and western China
title_short A deep learning-based hybrid method for PM2.5 prediction in central and western China
title_sort deep learning based hybrid method for pm2 5 prediction in central and western china
topic Long short-term memory (LSTM)
Transformer
Particle swarm optimization (PSO)
PM2.5 prediction
url https://doi.org/10.1038/s41598-025-95460-6
work_keys_str_mv AT zuhanliu adeeplearningbasedhybridmethodforpm25predictionincentralandwesternchina
AT zihaifang adeeplearningbasedhybridmethodforpm25predictionincentralandwesternchina
AT yuanhaohu adeeplearningbasedhybridmethodforpm25predictionincentralandwesternchina
AT zuhanliu deeplearningbasedhybridmethodforpm25predictionincentralandwesternchina
AT zihaifang deeplearningbasedhybridmethodforpm25predictionincentralandwesternchina
AT yuanhaohu deeplearningbasedhybridmethodforpm25predictionincentralandwesternchina