PM2.5 hourly concentration prediction based on graph capsule networks

Suhua Wang; Zhen Huang; Hongjie Ji; Huinan Zhao; Guoyan Zhou; Xiaoxin Sun; Suhua Wang; Zhen Huang; Hongjie Ji; Huinan Zhao; Guoyan Zhou; Xiaoxin Sun

doi:10.3934/era.2023025

Electronic Research Archive

2023, Volume 31, Issue 1: 509-529. doi: 10.3934/era.2023025

Previous Article Next Article

Research article Special Issues

PM2.5 hourly concentration prediction based on graph capsule networks

1.
Computer Department, Changchun Humanities and Sciences College, Changchun 130117, China
2.
The University of Science and Technology of China, Department of Computer Science, Hefei 230026, China
3.
School of Information Science and Technology, Northeast Normal University, Changchun 130117, China
4.
School of Environmental Science, Northeast Normal University, Changchun 130117, China

Received: 24 August 2022 Revised: 08 October 2022 Accepted: 28 October 2022 Published: 14 November 2022

In this paper, we use a graph capsule network to capture the spatial dependence of air quality data and meteorological data among cities, then use an LSTM network to model the temporal dependence of air pollution levels in specific cities and finally implement PM2.5 concentration prediction. We propose a graph-capsule-LSTM model based on a graph-capsule network and an LSTM network. The model uses a graph capsule network to model the neighboring feature information of the target city and then combines the local data of the target city to form the final feature vector. The feature mapping on the time axis is then used to obtain the temporal feature sequences of the target nodes, which are fed into the LSTM network for learning and prediction. Experiments show that the method achieves better results than the latest baseline model in the PM2.5 prediction task. While demonstrating that the capsule network outperforms the convolutional network, it also shows that this capsule network is very competent for the task of PM2.5 prediction.
- PM2.5 Hourly Concentration Prediction,
- Graph Capsule Network,
- LSTM
Citation: Suhua Wang, Zhen Huang, Hongjie Ji, Huinan Zhao, Guoyan Zhou, Xiaoxin Sun. PM2.5 hourly concentration prediction based on graph capsule networks[J]. Electronic Research Archive, 2023, 31(1): 509-529. doi: 10.3934/era.2023025

Related Papers:

Abstract

In this paper, we use a graph capsule network to capture the spatial dependence of air quality data and meteorological data among cities, then use an LSTM network to model the temporal dependence of air pollution levels in specific cities and finally implement PM2.5 concentration prediction. We propose a graph-capsule-LSTM model based on a graph-capsule network and an LSTM network. The model uses a graph capsule network to model the neighboring feature information of the target city and then combines the local data of the target city to form the final feature vector. The feature mapping on the time axis is then used to obtain the temporal feature sequences of the target nodes, which are fed into the LSTM network for learning and prediction. Experiments show that the method achieves better results than the latest baseline model in the PM2.5 prediction task. While demonstrating that the capsule network outperforms the convolutional network, it also shows that this capsule network is very competent for the task of PM2.5 prediction.

References

[1]	World Health Organization, WHO. Ambient (Outdoor) Air Quality and Health.Retrieved. 2016. Available from: http://www.who.int/mediacentre/factsheets/fs313/en/ (Accessed date: 14 September 2017)
[2]	Z. Shang, T. Deng, J. He, X. Duan, A novel model for hourly PM2. 5 concentration prediction based on CART and EELM, Sci. Total Environ., 651 (2019), 3043–3052. https://doi.org/10.1016/j.scitotenv.2018.10.193 doi: 10.1016/j.scitotenv.2018.10.193
[3]	A. Kumar, R. S. Patil, A. K. Dikshit, S. Islam, R. Kumar, Evaluation of control strategies for industrial air pollution sources using American meteorological society/ environmental protection agency regulatory model with simulated meteorology by weather research and forecasting model, J. Cleaner Prod., 116 (2016), 110–117. https://doi.org/10.1016/j.jclepro.2015.12.079 doi: 10.1016/j.jclepro.2015.12.079
[4]	F. Jiang, Y. Q. Qiao, PM2.5 concentration prediction based on sample entropy and improved extreme learning machine, Statistics & Decision, 37 (2021), 166–171.
[5]	H. Y. Luo, D. Y. Wang, Y. L. Liu, S. Wei, Y. B. Lin, PM2.5 Concentration forecasting based on two-layer decomposition technique and improved extreme learning machine, Syst. Eng.-Theo. Practice, 38 (2018), 1321–1330.
[6]	S. Moisan, R. Herrera, A. Clements, A dynamic multiple equation approach for forecasting PM2. 5 pollution in Santiago, Chile, Int. J. Forecast., 34 (2018), 566–581. https://doi.org/10.1016/j.ijforecast.2018.03.007 doi: 10.1016/j.ijforecast.2018.03.007
[7]	H. X. Jiang, J. Tian, C. H. Sun, Ensemble model of recursive random forest and multilayer neural network for PM2.5 prediction, Syst. Eng., 38 (2020), 14–24.
[8]	W. Sun, J. Y. Sun, Daily PM2.5 concentration prediction based on principal component analysis and LSSVM optimized by cuckoo search algorithm, J. Environ. Manag., 188 (2017), 144–152. https://doi.org/10.1016/j.jenvman.2016.12.011 doi: 10.1016/j.jenvman.2016.12.011
[9]	Q. Sun, Y. M. Zhu, X. M. Chen, A. Xu, X. Peng, A hybrid deep learning model with multi-source data for PM 2.5 concentration forecast, Air Qual. Atmos. Hlth., 14 (2020), 1–11. https://doi.org/10.1007/s11869-020-00954-z doi: 10.1007/s11869-020-00954-z
[10]	W. T. Yang, M. Deng, F. Xu, H. Wang, Prediction of hourly PM2. 5 using a space-time support vector regression model, Atmos. Environ., 181 (2018), 12–19. https://doi.org/10.1016/j.atmosenv.2018.03.015 doi: 10.1016/j.atmosenv.2018.03.015
[11]	G. Shi, Y. Leung, J. S. Zhang, T. Fung, F. Du, Y. Zhou, A novel method for identifying hotspots and forecasting air quality through an adaptive utilization of spatio-temporal information of multiple factors, Sci. Total Environ., 759 (2021), 143–513. https://doi.org/10.1016/j.scitotenv.2020.143513 doi: 10.1016/j.scitotenv.2020.143513
[12]	Q. P. Zhou, H. Y. Jiang, J. Z. Wang, J. L. Zhou, A hybrid model for PM2. 5 forecasting based on ensemble empirical mode decomposition and a general regression neural network, Sci. Total Environ., 496 (2014), 264–274. https://doi.org/10.1016/j.scitotenv.2014.07.051 doi: 10.1016/j.scitotenv.2014.07.051
[13]	K. R. Weng, M. Liu, Q. Liu, An integrated prediction model of PM2.5 concentration based on TPE-XGBOOST and LassoLars, Syst. Eng.-Theo. Practice, 40 (2020), 748–760.
[14]	P. P. Xiong, S. Huang, M. Peng, X. Wu, Examination and prediction of fog and haze pollution using a multi-variable grey model based on interval number sequences, Appl. Math. Model., 77 (2020), 1531–1544. https://doi.org/10.1016/j.apm.2019.09.027 doi: 10.1016/j.apm.2019.09.027
[15]	Z. C. Wang, L. R. Chen, J. M. Zhu, H. Chen, H. Yuan, Double decomposition and optimal combination ensemble learning approach for interval-valued AQI forecasting using streaming data, Environ. Sci. Pollut. Res., 27 (2020), 37802–37817. https://doi.org/10.1007/s11356-020-09891-x doi: 10.1007/s11356-020-09891-x
[16]	J. Xu, L. Chen, M. Lv, C. Zhan, S. Chen, J. Chang, HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method, arXiv, (2021), arXiv: 2101.04264. 86.
[17]	H.C. Chen, K.T. Putra, J. A. Chun-WeiLin, Novel Prediction Approach for Exploring PM2.5 Spatiotemporal Propagation Based on Convolutional Recursive Neural Networks, arXiv, (2021) arXiv: 2101.06213. 96.
[18]	R. Yan, J. Liao, J. Yang, W. Sun, M. Nong, F. Li, Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering, Expert Syst. Appl., 169 (2021), 114513. https://doi.org/10.1016/j.eswa.2020.114513 doi: 10.1016/j.eswa.2020.114513
[19]	X. L. Dai, J. J. Liu, Y. L. Li, A recurrent neural network using historical data to predict time series indoor PM2.5 concentrations for residential buildings, Indoor Air, 31 (2021), 1228–1237. https://doi.org/10.1111/ina.12794 doi: 10.1111/ina.12794
[20]	D. Seng, Q Zhang, X. Zhang, G. Chen, X. Chen, Spatiotemporal prediction of air quality based on LSTM neural network, Alex. Eng. J., 60 (2021), 2021–2032. https://doi.org/10.1016/j.aej.2020.12.009 doi: 10.1016/j.aej.2020.12.009

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)