A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network
Environmental Pollution · 2023
DOI: 10.1016/j.envpol.2023.121075 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Pollution, 2023. Verfasst von Cui-Lin Wu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Center for ITS and UAV Applications Research, State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, S…. Hauptthemen laut MEDLINE: Air Pollutants, Deep Learning, Air Pollution, Environmental Pollutants. Die Arbeit wurde bisher 81-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Short-term prediction of urban air quality is critical to pollution management and public health. However, existing studies have failed to make full use of the spatiotemporal correlations or topological relationships among air quality monitoring networks (AQMN), and hence exhibit low precision in regional prediction tasks. With this consideration, we proposed a novel deep learning-based hybrid model of Res-GCN-BiLSTM combining the residual neural network (ResNet), graph convolutional network (GCN), and bidirectional long short-term memory (BiLSTM), for predicting short-term regional NO2 and O3 concentrations. Auto-correlation analysis and cluster analysis were first utilized to reveal the inherent temporal and spatial properties respectively. They demonstrated that there existed temporal daily periodicity and spatial similarity in AQMN. Then the identified spatiotemporal properties were sufficiently leveraged, and monitoring network topological information, as well as auxiliary pollutants and meteorology were also adaptively integrated into the model. The hourly observed data from 51 air quality monitoring stations and meteorological data in Shanghai were employed to evaluate it. Results show that the Res-GCN-BiLSTM model was better adapted to the pollutant characteristics and improved the prediction accuracy, with nearly 11% and 17% improvements in mean absolute error for NO2 and O3, respectively compared to the best performing baseline model. Among the three types of monitoring stations, traffic monitoring stations performed the best for O3, but the worst for NO2, mainly due to the impacts of intensive traffic emissions and the titration reaction. These findings illustrate that the hybrid architecture is more suitable for regional pollutant concentration.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Center for ITS and UAV Applications Research, State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.
- Center for ITS and UAV Applications Research, State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China. Electronic addr…
- Department of Civil and Environmental Engineering, Northeastern University, 360 Huntington Ave., Boston, MA, 02115, USA.
- International Center for Adaptation Planning and Design, College of Design, Construction and Planning, University of Florida, PO Box 115706, Gainesville, FL, 32611-5706, USA.
- Shanghai Environmental Monitoring Center, Shanghai, 200235, China.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wu, C. L., He, H. D., Song, R. F., Zhu, X. H., Peng, Z. R., Fu, Q. Y., & Pan, J. (2023). A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network. Environmental Pollution. https://doi.org/10.1016/j.envpol.2023.121075
Vancouver
Wu CL, He HD, Song RF, Zhu XH, Peng ZR, Fu QY, et al. A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network. Environmental Pollution. 2023. doi:10.1016/j.envpol.2023.121075
BibTeX
@article{Wu2023,
author = {Wu, Cui-Lin and He, Hong-di and Song, Rui-Feng and Zhu, Xing-Hang and Peng, Zhong-Ren and Fu, Qing-Yan and Pan, Jun},
title = {A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network},
journal = {Environmental Pollution},
year = {2023},
doi = {10.1016/j.envpol.2023.121075}
}
EUVIMED