Hybrid TCN-BiGRU model for accurate air quality index prediction
Environmental Pollution · 2026-02 · 391 · 127577
DOI: 10.1016/j.envpol.2025.127577 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Pollution, 2026-02. Verfasst von Wenbiao Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China. Electronic address: yangwb@gzhu.edu.cn. Hauptthemen laut MEDLINE: Air Pollution, Environmental Monitoring, Air Pollutants, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: Ministry of Education of the People's Republic of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate Air Quality Index (AQI) forecasting is critical for pollution control and public health protection, yet traditional methods struggle to capture long-range temporal dependencies and bidirectional context in complex atmospheric dynamics. We propose TCN-BiGRU, a novel deep learning framework that integrates Temporal Convolutional Network (TCN) and Bidirectional Gated Recurrent Unit (BiGRU) through a cascaded architecture with residual connections. The TCN component extracts multi-scale temporal features via dilated convolutions with exponentially increasing receptive fields, while BiGRU processes these enriched features bidirectionally to capture both past and future contextual dependencies. We evaluated TCN-BiGRU against 13 baseline models and 3 state-of-the-art models from 2025 across 16 seasonal-regional scenarios using datasets from Beijing (2022 and 2023), Guangzhou (2023), and Shanghai (2023). TCN-BiGRU achieves RMSE improvements over the strongest 2025 SOTA model in all 16 seasonal-regional scenarios, with gains up to about 17% and R2 values consistently exceeding 0.876, while being 3.2-5.5× faster in inference than these SOTA models. Ablation studies confirm 25.5% performance improvement through synergistic effects of the cascaded architecture. Cross-year validation shows 8.3% performance degradation, while cross-city transfer learning achieves 74.2-82.7% of full local training performance with only 20% target data. These results demonstrate superior accuracy-efficiency trade-off and robust generalization across diverse geographic and climatic conditions. The source code is available at https://github.com/ProfYangPaperCode/TCN-BiGRU-for-Predicting-AQI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China. Electronic address: yangwb@gzhu.edu.cn.
- School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China. Electronic address: shangwl@gzhu.edu.cn.
- School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China. Electronic address: 202250000016@stu.hebut.edu.cn.
Förderung
- Ministry of Education of the People's Republic of China
- National Natural Science Foundation of China
Zitieren
APA
Yang, W., Shang, W., & Fatima, T. (2026). Hybrid TCN-BiGRU model for accurate air quality index prediction. Environmental Pollution, 391, 127577. https://doi.org/10.1016/j.envpol.2025.127577
Vancouver
Yang W, Shang W, Fatima T. Hybrid TCN-BiGRU model for accurate air quality index prediction. Environmental Pollution. 2026;391:127577. doi:10.1016/j.envpol.2025.127577
BibTeX
@article{Yang2026,
author = {Yang, Wenbiao and Shang, Wenli and Fatima, Tehreem},
title = {Hybrid TCN-BiGRU model for accurate air quality index prediction},
journal = {Environmental Pollution},
year = {2026},
volume = {391},
pages = {127577},
doi = {10.1016/j.envpol.2025.127577}
}
EUVIMED