Skip to content
DraconiticResearch
Search Sources API
179,152 studies31 sourcesUpdated 53 min ago
Peer-reviewedCC BY 4.0PLOS One

A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm

  • Xiaoliang Zhao1
  • Pinyuan Qiao2
  • Bandna Bharti3
  • Hanliang Li4
  • Shitong Yang5
  • Qi Shi6
  • Qiuhong Qin
  • Jundian Chen
6 affiliations
  1. 1Department of Environmental Science and Engineering, Liaoning Technical University, Fuxin, Liaoning, China
  2. 2Collaborative Innovation Center of Mine Major Disaster Prevention and Environmental Restoration, Fuxin, Liaoning, China
  3. 3Department of Chemistry, DAV University, Jalandhar, Punjab, India
  4. 4Inner Mongolia Shendong Tianlong Group Co., Ltd., Ordos, Inner Mongolia, China
  5. 5Liaoning Geo-Mineral Investment and Development Group Co., Ltd., Shenyang, Liaoning, China
  6. 6Liaoning Provincial Geology and Mineral Resources Group Mining Co., Ltd., Shenyang, Liaoning, China
Open at sourcePDFDOICite

Abstract

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.

Related

  1. Machine Learning-Based Hydrological Drought Prediction Integrating Teleconnections and Hydrological Memory in a Semi-Arid Basin, Algeria
    Okan Mert Katipoğlu, Mohammed Achite, Veysi Kartal +2
    AtmospherePeer-reviewedCC BY12 citedClimate scienceOpenAlex
  2. A hybrid spatio-temporal deep learning framework for urban travel time prediction and intelligent routing: Integrating recurrent and graph neural networks
    Zahra Rezaei, Alireza Sharifi
    Sustainable FuturesPeer-reviewedCC BYFull textEnvironmental science & pollutionDOAJ
  3. Machine Learning-Based NOx Prediction and Combustion Optimization for a Coal-Fired Boiler: The Role of Feature Engineering
    Peixuan Li, Dining Ma, Shicong Jiang +1
    ACS OmegaPeer-reviewedCC BY-NC-ND 4.0Full textEnvironmental science & pollutionCrossrefEurope PMC
  4. Integrating high-resolution magnetic surveys and metaheuristic optimization for quantitative characterization of subsurface magnetic sources in a municipal landfill
    Eko Minarto, Z. R. Almiranda Lesar
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textGeophysics & seismologyCrossref
  5. Integrating Molecular Docking, Dynamics, and AI-Based ADMET Prediction to Decipher the Toxicity Profile of Isometamidium Chloride Against Animal Trypanosomiasis
    Journal of xenobioticsPeer-reviewedCC BYFull textEnvironmental science & pollutionEurope PMC

Cite

BibTeXRIS
BibTeX
@article{zhao2026novel,
  title = {{A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm}},
  author = {Xiaoliang Zhao and Pinyuan Qiao and Bandna Bharti and Hanliang Li and Shitong Yang and Qi Shi and Qiuhong Qin and Jundian Chen},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0358271},
  url = {https://doi.org/10.1371/journal.pone.0358271},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm
AU  - Xiaoliang Zhao
AU  - Pinyuan Qiao
AU  - Bandna Bharti
AU  - Hanliang Li
AU  - Shitong Yang
AU  - Qi Shi
AU  - Qiuhong Qin
AU  - Jundian Chen
PY  - 2026
DA  - 2026/09/15
JO  - PLOS One
DO  - 10.1371/journal.pone.0358271
UR  - https://doi.org/10.1371/journal.pone.0358271
AB  - 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.
SN  - 1932-6203
ER  -