Abstract
Massive studies focus on the prediction of main pollutants, to improve air quality by revealing the evolution of pollutants. However, existing prediction methods mostly emphasize the fitting analysis of time series, but ignore the spatial propagation effect among nearby places, resulting in a low prediction accuracy. To address this issue, this paper proposes a novel synthesis prediction method to simultaneously excavate the time series changing law and the spatial propagation effect. This method combines a characterization model named air quality spatial-temporal network (AQSTN) and a neural network model called graph convolution neural network (GCN). Firstly, by calculating three correlation coefficients, the time series of most related meteorological factors and aerosol data are gained for feature construction. The geographic distances between locations are computed to evaluate the spatial propagation cost. After that, AQSTN with locations as nodes and propagation relations as edges is constructed, compositing the temporal and spatial relationships. The network is regarded as graph data and input into GCN in chronological order. Secondly, GCN processing graph-structured data fits the optimal parameters in the training stage, simultaneously analyzes the spatial and temporal dimensions of the target site and its adjacent sites. And, the predicted \({\rm{PM}}_{2.5}\) concentration is gained in the test stage. The near-surface monitoring data of Beijing-Tianjin-Hebei area are adopted for experiment. Compared with the second-best model, the RMSE value of AQSTN-GCN is 6.85% lower, MAE value is 13.79% lower, MSE value is 13.23% lower, and MAPE value is 21.53% lower.
Similar content being viewed by others
References
Lippmann M (1989) Health effects of ozone a critical review. Japca 39(5):672–695. https://doi.org/10.1080/08940630.1989.10466554
Bell ML, Goldberg R, Hogrefe C, Kinney PL, Knowlton K, Lynn B, Patz JA (2007) Climate change, ambient ozone, and health in 50 US cities. Clim Change 82(1):61–76. https://doi.org/10.1007/s10584-006-9166-7
Nel A (2005) Air pollution-related illness: effects of particles. Science 308(5723):804–806. https://doi.org/10.1126/science.1108752
Pope CA III, Hansen JC, Kuprov R, Sanders MD, Anderson MN, Eatough DJ (2011) Vascular function and short-term exposure to fine particulate air pollution. J Air Waste Manag Assoc 61(8):858–863. https://doi.org/10.3155/1047-3289.61.8.858
Lelieveld J, Evans JS, Fnais M, Giannadaki D, Pozzer A (2015) The contribution of outdoor air pollution sources to premature mortality on a global scale. Nature 525(7569):367–371. https://doi.org/10.1038/nature15371
Ambient air pollution—a major threat to health and climate (2020) [Online] Available: http://www.who.int/airpollution/ambient/en/
Global Metrics for the Environment—The environmental performance index ranks countries performance on high-priority environmental issues (2020) [Online] Available: https://epi.envirocenter.yale.edu/results-overview
Hernandez RA (2015) Prevention and control of air pollution in China: a research agenda for science and technology studies. SAPI EN. S. Surveys and Perspectives Integrating Environment and Society (8.1)
Jin Y, Andersson H, Zhang S (2016) Air pollution control policies in China: a retrospective and prospects. Int J Environ Res Public Health 13(12):1219. https://doi.org/10.3390/ijerph13121219
Fu B, Kurisu K, Hanaki K, Che Y (2019) Influential factors of public intention to improve the air quality in China. J Clean Prod 209:595–607. https://doi.org/10.1016/j.jclepro.2018.10.192
Shepard D (1968) A two-dimensional interpolation function for irregularly-spaced data. In: Proceedings of the 1968 23rd ACM national conference, pp 517–524. https://doi.org/10.1145/800186.810616
Zheng Y, Liu F, Hsieh HP (2013) U-air: when urban air quality inference meets big data. In: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 1436–1444. https://doi.org/10.1145/2487575.2488188
Bai Y, Wu L, Qin K, Zhang Y, Shen Y, Zhou Y (2016) A geographically and temporally weighted regression model for ground-level PM2.5 estimation from satellite-derived 500 m resolution AOD. Remote Sens 8(3):262. https://doi.org/10.3390/rs8030262
Tang M, Wu X, Agrawal P, Pongpaichet S, Jain R (2016) Integration of diverse data sources for spatial PM2.5 data interpolation. IEEE Trans Multimed 19(2):408–417. https://doi.org/10.1109/TMM.2016.2613639
Goodin WR, McRae GJ, Seinfeld JH (1980) An objective analysis technique for constructing three-dimensional urban-scale wind fields. J Appl Meteorol 19(1):98–108
Vardoulakis S, Fisher BE, Pericleous K, Gonzalez-Flesca N (2003) Modelling air quality in street canyons: a review. Atmos Environ 37(2):155–182. https://doi.org/10.1016/s1352-2310(02)00857-9
Pisoni E, Clappier A, Degraeuwe B, Thunis P (2017) Adding spatial flexibility to source-receptor relationships for air quality modeling. Environ Model Softw 90:68–77. https://doi.org/10.1016/j.envsoft.2017.01.001
Jiang Z, Mao B, Meng X, Du X, Liu S, Li S (2010) An air quality forecast model based on the BP neural network of the samples self-organization clustering. In: 2010 Sixth international conference on natural computation, vol 3, pp 1523–1527. https://doi.org/10.1109/ICNC.2010.5582643
Reyes J, Abraham Sánchez (2013) Analysis of air quality data in Mexico city with clustering techniques based on genetic algorithms. In: International conference on electronics. IEEE. https://doi.org/10.1109/CONIELECOMP.2013.6525752
Sefidmazgi MG, Kordmahalleh MM, Homaifar A, Liess S (2015) Change detection in climate time series based on bounded-variation clustering. In: Machine learning and data mining approaches to climate science. Springer, Cham, pp 185–194. https://doi.org/10.1007/978-3-319-17220-0_17
Dincer NG, Akkuş Ö (2018) A new fuzzy time series model based on robust clustering for forecasting of air pollution. Ecol Inform 43:157–164. https://doi.org/10.1016/j.ecoinf.2017.12.001
Mahajan S, Liu HM, Tsai TC, Chen LJ (2018) Improving the accuracy and efficiency of PM2.5 forecast service using cluster-based hybrid neural network model. IEEE Access 6:19193–19204. https://doi.org/10.1109/ACCESS.2018.2820164
Zhao G, Huang G, He H, He H, Ren J (2019) Regional spatiotemporal collaborative prediction model for air quality. IEEE Access 7:134903–134919. https://doi.org/10.1109/ACCESS.2019.2941732
Soh PW, Chang JW, Huang JW (2018) Adaptive deep learning-based air quality prediction model using the most relevant spatial-temporal relations. IEEE Access 6:38186–38199. https://doi.org/10.1109/ACCESS.2018.2849820
Wen C, Liu S, Yao X, Peng L, Li X, Hu Y, Chi T (2019) A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. Sci Total Environ 654:1091–1099. https://doi.org/10.1016/j.scitotenv.2018.11.086
Byun DW, Schere KL (2005) Review of the governing equations, computational algorithms and other components of the models-3 community multiscale air quality (CMAQ) modeling system. Appl Mech Rev 59(2):51–78
Kindap T, Unal A, Chen SH, Hu Y, Odman MT, Karaca M (2006) Long-range aerosol transport from Europe to Istanbul, Turkey. Atmos Environ 40(19):3536–3547
Saide PE, Carmichael GR, Spak SN, Gallardo L, Osses AE, Mena-Carrasco MA, Pagowski M (2011) Forecasting urban PM10 and PM2.5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF-Chem CO tracer model. Atmos Environ 45(16):2769–2780
Stadlober E, Hörmann S, Pfeiler B (2008) Quality and performance of a PM10 daily forecasting model. Atmos Environ 42(6):1098–1109
Box GE, Jenkins GM, Reinsel GC, Ljung GM (2015) Time series analysis: forecasting and control, vol 22, 2nd edn. Wiley, New York, pp 199–201
Li C, Hsu NC, Tsay SC (2011) A study on the potential applications of satellite data in air quality monitoring and forecasting. Atmos Environ 45(22):3663–3675
Nguyen-Tuong D, Peters JR, Seeger M (2009) Local gaussian process regression for real time online model learning. In: Advances in neural information processing systems, pp 1193–1200
Cabaneros SM, Calautit JK, Hughes BR (2019) A review of artificial neural network models for ambient air pollution prediction. Environ Model Softw 119:285–304
Huang GB, Zhu QY, Siew CK, Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541), vol 2. IEEE, pp 985–990
Rumelhart DE, Hinton GE, Williams RJ (1986) Parallel distributed processing: explorations in the microstructure of cognition. Language 63(4):45–76
Fernandez S, Bunke H, Schmiduber J (2009) A novel connectionist system for improved unconstrained handwriting recognition. IEEE Trans Pattern Anal Mach Intell 31(5)
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473
Graves A, Mohamed A, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 6645–6649
Ong BT, Sugiura K, Zettsu K (2016) Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM 2.5. Neural Comput Appl 27(6):1553–1566
Athira V, Geetha P, Vinayakumar R, Soman KP (2018) Deepairnet: applying recurrent networks for air quality prediction. Proc Comput Sci 132:1394–1440
Qi Z, Wang T, Song G, Hu W, Li X, Zhang Z (2018) Deep air learning: interpolation, prediction, and feature analysis of fine-grained air quality. IEEE Trans Knowl Data Eng 30(12):2285–2297
Gu K, Qiao J, Lin W (2018) Recurrent air quality predictor based on meteorology-and pollution-related factors. IEEE Trans Ind Inf 14(9):3946–3955
Liu DR, Lee SJ, Huang Y, Chiu CJ (2020) Air pollution forecasting based on attention-based LSTM neural network and ensemble learning. Expert Syst 37(3):e12511
Zhou Y, Chang FJ, Chang LC, Kao IF, Wang YS (2019) Explore a deep learning multi-output neural network for regional multi-step-ahead air quality forecasts. J Clean Prod 209:134–145
Wang B, Yan Z, Lu J, Zhang G, Li T (2018) Deep multi-task learning for air quality prediction. In: International conference on neural information processing. Springer, Cham, pp 93–103
Sukittanon S, Surendran AC, Platt JC, Burges CJ (2004) Convolutional networks for speech detection. In: Eighth international conference on spoken language processing
Du S, Li T, Yang Y, Horng SJ (2019) Deep air quality forecasting using hybrid deep learning framework. IEEE Trans Knowl Data Eng
Feng F, Wu J, Sun W, Wu Y, Li H, Chen X (2018) Haze forecasting via deep LSTM. In: Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) joint international conference on Web and Big Data. Springer, Cham, pp 349–356
Huang CJ, Kuo PH (2018) A deep CNN-LSTM model for particulate matter (PM2.5) forecasting in smart cities. Sensors 18(7):2220
Qin D, Yu J, Zou G, Yong R, Zhao Q, Zhang B (2019) A novel combined prediction scheme based on CNN and LSTM for urban PM 2.5 concentration. IEEE Access 7:20050–20059
Barabási AL, Albert R (1999) Emergence of scaling in random networks. Science 286(5439):509–512. https://doi.org/10.1126/science.286.5439.509
Watts DJ, Strogatz SH (1998) Collective dynamics of small world networks. Nature 393(6684):440–442. https://doi.org/10.1038/30918
Strogatz SH (2001) Exploring complex networks. Nature 410(6825):268. https://doi.org/10.1038/35065725
Girvan M, Newman ME (2002) Community structure in social and biological networks. Proc Nat Acad Sci 99(12):7821–7826. https://doi.org/10.1073/pnas.122653799
Bullmore E, Sporns O (2009) Complex brain networks: graph theoretical analysis of structural and functional systems. Nat Rev Neurosci 10(3):186–198. https://doi.org/10.1038/nrn2575
Fortunato S (2009) Community detection in graphs. Phys Rep 486(3–5):75–174. https://doi.org/10.1016/j.physrep.2009.11.002
Lu ZM, Guo SZ (2012) A small-world network derived from the deterministic uniform recursive tree. Physica A 391(1–2):87–92. https://doi.org/10.1016/j.physa.2011.08.002
Mendes GA, Da Silva LR, Herrmann HJ (2012) Traffic gridlock on complex networks. Physica A 391(1–2):362–370. https://doi.org/10.1016/j.physa.2011.07.046
Wang Y, Cao J, Jin Z, Zhang H, Sun GQ (2013) Impact of media coverage on epidemic spreading in complex networks. Physica A 392(23):5824–5835. https://doi.org/10.1016/j.physa.2013.07.067
Zhao G, Huang G, He H, Wang Q (2019) Innovative spatial-temporal network modeling and analysis method of air quality. IEEE Access 7:26241–26254. https://doi.org/10.1109/ACCESS.2019.2900997
Bruna J, Zaremba W, Szlam A, LeCun Y (2013) Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203
Acknowledgements
The authors are grateful to valuable comments and suggestions of the reviewers and editors. This work was supported by the National Natural Science Foundation of China under Grant 61772451; and the Graduate Innovative Funding Project of Hebei Province under Grant CXZZBS2020061.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
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.
Appendix. The complex network
Appendix. The complex network
A complex network [52,53,54] can be regarded as a set of individuals, which have independent characteristics and are interconnected with each other. In this set, each individual can be regarded as a node in the graph, and the interconnection between nodes can be regarded as an edge in the graph. A simple undirected unweighted network can be denoted by G(V, E). Here, \(V=\left\{ v_1, v_2, \dots , v_N\right\}\) is the node set, and \(E=\left\{ e_1, e_2, \dots , e_M \right\}\) is the edge set. Each edge corresponds to a tuple of nodes, that is \(e_x=\left\{ v_i,v_j \right\}\). Normally, any complex system that contains a large number of constituent units (or subsystems) can be studied as a complex network when the constituent units are abstracted into nodes and the interactions between the units are abstracted into edges [55,56,57,58,59,60]. Complex networks generally have the following three characteristics (Fig. 14).
Small world Despite the large scale, most networks can find a fairly short path between any two nodes. Simply speaking, there exits the fact that a single node that have a small number of interrelationships with others can connect the whole world. Supposing that the distance between two nodes \(v_i\) and \(v_j\), marked as \(d_{ij}\), is equal to the number of edges in the shortest path connecting the two nodes, the average distance in graph G(V, E) can be expressed as \(\left\langle d \right\rangle =\frac{1}{N(N-1)}\sum _{i\ne j}d_{ij}\) where N is the number of nodes. Then, if the average degree is fixed, the network is considered to have a small-world effect when the average distance increases at or less than the logarithmic rate following the growth of the number of nodes.
Scale-free p(k) is defined as the proportion of the number of nodes with the degree of k in the network to the total number of nodes, namely the degree distribution of nodes. The empirical study shows that the degree distribution of complex networks approximately follows the form of power function, i.e., \(p(k)\propto k^ {-\gamma }\). Here, \(\gamma\) is the power exponent. Since the function has the invariant power exponent, such networks are called scale-free networks. The power function decays slowly, allowing the existence of some high-degree nodes (pivot nodes), which have a critical impact on the overall structure and function of the network.
Community structure Intuitively speaking, community structure means that the network consists of many communities, with close boundaries within communities and few boundaries between communities, as shown in Fig. 12. The most widely used measure of community is called Modularity. Modularity is essentially a description of the extent to which a real network has more internal edges than the corresponding random network, defined as \(Q=\frac{1}{2M} \sum _{i\ne j}\left( A_{ij}-\frac{k_ik_j}{2M} \right) \delta ^{ij}\). Here, A is adjacency matrix, M is the total number of edges. If node \(v_i\) and node \(v_j\) belong to the same community, \(\delta ^{ij}=1\), otherwise 0.
Rights and permissions
About this article
Cite this article
Zhao, G., He, H., Huang, Y. et al. Near-surface PM2.5 prediction combining the complex network characterization and graph convolution neural network. Neural Comput & Applic 33, 17081–17101 (2021). https://doi.org/10.1007/s00521-021-06300-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06300-3