Abstract
With the industrialization of society, air pollution has become a critical environmental issue, leading to excessive morbidity and mortality from cardiovascular and respiratory diseases in humans. Accurate air pollution prediction has strongly promoted air quality control, which is important for human health. However, previous studies have failed to model spatiotemporal dependencies simultaneously with non-Euclidean distributions considering meteorological factors. In this study, a novel multigraph convolutional neural network for air pollution prediction is proposed. First, a spatial graph, an air pollution pattern graph and a meteorological pattern graph are constructed to model different relationships among non-Euclidean areas. Second, the graph convolutional network is applied to learn and incorporate the information of neighbour nodes of the corresponding graph, and then the graphs after convolution are fused. Finally, the fused matrix of GCNs is input into the gate recurrent units to capture temporal dependencies. Experimental results on the real dataset collected at air quality monitoring stations in Beijing validate the effectiveness of our proposed model.
Similar content being viewed by others
References
Abhilash M, Thakur A, Gupta D et al (2018) Time series analysis of air pollution in bengaluru using ARIMA model. In: Ambient communications and computer systems. Springer, pp 413–426
Aditya C, Deshmukh CR, Nayana D et al (2018) Detection and prediction of air pollution using machine learning models. In: International journal of engineering trends and technology (IJETT), pp 204–207
Athira V, Geetha P, Vinayakumar R et al (2018) Deepairnet: applying recurrent networks for air quality prediction. Procedia Comput Sci 132:1394–1403
Chae S, Shin J, Kwon S et al (2021) PM10 and PM2.5 real-time prediction models using an interpolated convolutional neural network. Sci Reports 11(1):1–9
Chang FJ, Chang LC, Kang CC et al (2020) Explore spatio-temporal PM2.5 features in northern Taiwan using machine learning techniques. Sci Total Environment 736:139,656
Chen JC, Wu YJ (2020) Discrete-time Markov chain for prediction of air quality index. J Ambient Intell Humanized Comput, p 1–10
Crouse DL, Goldberg MS, Ross NA (2009) A prediction-based approach to modelling temporal and spatial variability of traffic-related air pollution in montreal, canada. Atmos Environ 43(32):5075–5084
Dairi A, Harrou F, Khadraoui S, et al. (2021) Integrated multiple directed attention-based deep learning for improved air pollution forecasting. IEEE Trans Instrum Meas 70:1–15
Du S, Li T, Yang Y, et al. (2019) Deep air quality forecasting using hybrid deep learning framework. IEEE Trans Knowl Data Eng 33(6):2412–2424
Espinosa R, Palma J, Jiménez F, et al. (2021) A time series forecasting based multi-criteria methodology for air quality prediction. Appl Soft Comput 113:107,850
Faraji M, Nadi S, Ghaffarpasand O et al (2022) An integrated 3D CNN-GRU deep learning method for short-term prediction of PM2.5 concentration in urban environment. Sci Total Environment 834:155,324
Ge L, Wu K, Zeng Y et al (2021) Multi-scale spatiotemporal graph convolution network for air quality prediction. Appl Intell 51(6):3491–3505
Gu K, Zhou Y, Sun H et al (2020) Prediction of air quality in Shenzhen based on neural network algorithm. Neural Comput Applic 32(7):1879–1892
Khatibi T, Karampour N (2021) Predicting the number of hospital admissions due to mental disorders from air pollutants and weather condition descriptors using stacked ensemble of deep convolutional models and LSTM models (SEDCMLM). J Cleaner Production 280:124,410
Leong W, Kelani R, Ahmad Z (2020) Prediction of air pollution index (API) using support vector machine (SVM). J Environmental Chem Eng 8(3):103,208
Li S, Xie G, Ren J et al (2020) Urban PM2.5 concentration prediction via attention-based CNN–LSTM. Appl Sci 10(6):1953
Liu C, Huang J, Hu XM et al (2021) Evaluation of WRF-chem simulations on vertical profiles of PM2.5 with UAV observations during a haze pollution event. Atmos Environ 252:118,332
Liu Y, Zhou Y, Lu J (2020) Exploring the relationship between air pollution and meteorological conditions in China under environmental governance. Sci Rep 10(1):1–11
Ma J, Li Z, Cheng J C et al (2020) Air quality prediction at new stations using spatially transferred bi-directional long short-term memory network. Sci Total Environment 705:135,771
Masood A, Ahmad K (2021) A review on emerging artificial intelligence (AI) techniques for air pollution forecasting: fundamentals, application and performance. J Cleaner Production 322:129,072
Organisation WH (2021) Ambient (outdoor) air pollution. https://www.who.int/news-room/fact-sheets/detail/ambient-(outdoor)-air-quality-and-health
Pak U, Ma J, Ryu U et al (2020) Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: a case study of Beijing, China. Sci Total Environment 699:133,561
Qi Y, Li Q, Karimian H et al (2019) A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory. Sci Total Environ 664:1–10
Qi Z, Wang T, Song G et al (2018) Deep air learning: interpolation, prediction, and feature analysis of fine-grained air quality. IEEE Trans Knowl Data Eng 30(12):2285–2297
Ruchiraset A, Tantrakarnapa K (2018) Time series modeling of pneumonia admissions and its association with air pollution and climate variables in Chiang Mai Province, Thailand. Environ Sci Pollution Res 25(33):33,277–33,285
Shams SR, Jahani A, Kalantary S et al (2021) The evaluation on artificial neural networks (ANN) and multiple linear regressions (MLR) models for predicting SO2 concentration. Urban Climate 37:100,837
Sharma E, Deo RC, Soar J et al (2022) Novel hybrid deep learning model for satellite based pm10 forecasting in the most polluted Australian hotspots. Atmos Environ 279:119,111
Shih S Y, Sun F K, Hy Lee (2019) Temporal pattern attention for multivariate time series forecasting. Mach Learn 108(8):1421–1441
Wang J, Zhou Q, Zhang X (2018) Wind power forecasting based on time series ARMA model. In: IOP conference series: earth and environmental science. IOP Publishing, p 022015
Wang J, Li J, Wang X et al (2021) Air quality prediction using CT-LSTM. Neural Comput Appl 33(10):4779–4792
Wei W, Ramalho O, Malingre L et al (2019) Machine learning and statistical models for predicting indoor air quality. Indoor Air 29(5):704–726
Wen C, Liu S, Yao X et al (2019) A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. Sci Total Environ 654:1091–1099
Xiao X, Jin Z, Wang S et al (2022) A dual-path dynamic directed graph convolutional network for air quality prediction. Sci Total Environ 827:154,298
Yang X, Wu Q, Zhao R et al (2019) New method for evaluating winter air quality: PM2.5 assessment using community multi-scale air quality modeling (CMAQ) in Xi’an. Atmos Environ 211:18–28
Yang X, Liang F, Li J et al (2020) Associations of long-term exposure to ambient PM2.5 with mortality in Chinese adults: a pooled analysis of cohorts in the china-PAR project. Environ Int 138:105,589
Yang Z (2020) Dct-based least-squares predictive model for hourly AQI fluctuation forecasting. J Environ Inf, vol 36(1)
Zhang B, Zou G, Qin D et al (2021) A novel encoder-decoder model based on read-first LSTM for air pollutant prediction. Sci Total Environ 765:144,507
Zhang Y, Thorburn PJ (2022) Handling missing data in near real-time environmental monitoring: a system and a review of selected methods. Futur Gener Comput Syst 128:63–72
Zhao J, Deng F, Cai Y et al (2019) Long short-term memory-fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. Chemosphere 220:486–492
Acknowledgements
This work was supported by National Natural Science Foundation of China, grant numbers 62107006, 52102374; National Key Research and Development Program of China, grant number 2020YFC1512004; Natural Science Basic Research Plan in Shaanxi Province of China, grant number 2021JC-27; Fundamental Research Funds for the Central Universities, Chang’an University, grant numbers 300102341101 and 300102341306.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, J., Yuan, C., Dong, S. et al. A novel spatiotemporal multigraph convolutional network for air pollution prediction. Appl Intell 53, 18319–18332 (2023). https://doi.org/10.1007/s10489-022-04418-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04418-y