EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PM2.5 Concentration Prediction Based on STL-TimesNet-TimeXer Hybrid Framework

Siqi Xiong, Zuhan Liu, Yan Li, Zonghao Nie

Atmosphere · 29.05.2026 · 17 (6) · 557

DOI: 10.3390/atmos17060557 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Atmosphere, online erschienen am 29.05.2026. Verfasst von Siqi Xiong und 3 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province, College Student Innovation and Entrepreneurship Training Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a hybrid forecasting framework that integrates Seasonal-Trend decomposition using LOESS (the following abbreviations are referred to as STL) with two time series models, TimesNet and TimeXer. To capture the complex periodic characteristics of the PM2.5 series, the original data are first decomposed into trend, seasonal and residual components via STL. The trend and seasonal components are then predicted using TimesNet, which maps one-dimensional time series into a two-dimensional representation to better model multi-scale periodicities and temporal dependencies. In parallel, the residual component is forecast using TimeXer, which incorporates exogenous variables to improve the modeling of endogenous dynamics. The final PM2.5 prediction is obtained by aggregating the forecasts of the three components. Experimental results demonstrate that the proposed STL-TimesNet-TimeXer model achieves high predictive accuracy, with an R2 of 0.969, MAE of 2.834, MSE of 19.063, and MAPE of 6.435. Comparative analyses against single-model baselines further confirm that STL-based decomposition significantly enhances forecasting performance, indicating that STL provides an effective and interpretable approach for modeling PM2.5 time series.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangxi Province
  • College Student Innovation and Entrepreneurship Training Program

Zitieren

APA

Xiong, S., Liu, Z., Li, Y., & Nie, Z. (2026). PM2.5 Concentration Prediction Based on STL-TimesNet-TimeXer Hybrid Framework. Atmosphere, 17(6), 557. https://doi.org/10.3390/atmos17060557

Vancouver

Xiong S, Liu Z, Li Y, Nie Z. PM2.5 Concentration Prediction Based on STL-TimesNet-TimeXer Hybrid Framework. Atmosphere. 2026;17(6):557. doi:10.3390/atmos17060557

BibTeX
@article{Xiong2026,
  author = {Xiong, Siqi and Liu, Zuhan and Li, Yan and Nie, Zonghao},
  title = {PM2.5 Concentration Prediction Based on STL-TimesNet-TimeXer Hybrid Framework},
  journal = {Atmosphere},
  year = {2026},
  volume = {17},
  number = {6},
  pages = {557},
  doi = {10.3390/atmos17060557}
}
Kostenlos starten →