EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatiotemporal Analysis and Deep Learning-Based Prediction of Air Pollution in China, 2015–2024

Kai Tan, Qianjun Ren, Yiting Huo, Lu Ran, Xiaofang Xu, Li Cao, Qianying Xiang, Huirong Duan, Shuhan Wang, Jisheng Nie, Xiujuan Yang

Atmosphere · 30.06.2026 · 17 (7) · 659

DOI: 10.3390/atmos17070659 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Atmosphere, online erschienen am 30.06.2026. Verfasst von Kai Tan und 10 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shanxi Province Postgraduate Academic Innovation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Air quality in China has markedly improved over the past decade, yet pollution levels remain high and continue to threaten public health. This study analyzed the spatiotemporal variations in six air pollutants (PM2.5, PM10, SO2, NO2, O3, CO) across seven regions in China (2015–2024) using Kriging interpolation. The performance of Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), and Convolutional Neural Network-Long Short-term Memory (CNN-LSTM) models was assessed using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2) metrics. Results showed that all pollutants exhibited overall declining trends, with SO2 depicting the largest reduction (69.53%), while O3 displayed intermittent increases from 2017 to 2024. North China recorded both the highest concentrations and the greatest reductions in PM2.5, SO2, and CO, whereas Southwest and South China maintained the lowest overall levels. Among the predictive models, LSTM achieved the highest overall accuracy (mean RMSE = 1.802, mean MAE = 0.915, R2 > 0.99). These findings provide a comprehensive depiction of China’s air pollution evolution and highlight the potential of deep learning for region-specific air quality prediction and policy design. The results offer a quantitative foundation for optimizing differentiated control strategies and advancing precision air quality management.

Förderung

  • National Natural Science Foundation of China
  • Shanxi Province Postgraduate Academic Innovation Project

Zitieren

APA

Tan, K., Ren, Q., Huo, Y., Ran, L., Xu, X., Cao, L., Xiang, Q., Duan, H., Wang, S., Nie, J., & Yang, X. (2026). Spatiotemporal Analysis and Deep Learning-Based Prediction of Air Pollution in China, 2015–2024. Atmosphere, 17(7), 659. https://doi.org/10.3390/atmos17070659

Vancouver

Tan K, Ren Q, Huo Y, Ran L, Xu X, Cao L, et al. Spatiotemporal Analysis and Deep Learning-Based Prediction of Air Pollution in China, 2015–2024. Atmosphere. 2026;17(7):659. doi:10.3390/atmos17070659

BibTeX
@article{Tan2026,
  author = {Tan, Kai and Ren, Qianjun and Huo, Yiting and Ran, Lu and Xu, Xiaofang and Cao, Li and Xiang, Qianying and Duan, Huirong and Wang, Shuhan and Nie, Jisheng and Yang, Xiujuan},
  title = {Spatiotemporal Analysis and Deep Learning-Based Prediction of Air Pollution in China, 2015–2024},
  journal = {Atmosphere},
  year = {2026},
  volume = {17},
  number = {7},
  pages = {659},
  doi = {10.3390/atmos17070659}
}
Kostenlos starten →