Integrated Predictor Based on Decomposition Mechanism for PM2.5 Long-Term Prediction
Source abstract
Abstract
It is crucial to predict PM2.5 concentration for early warning regarding and the control of air pollution. However, accurate PM2.5 prediction has been challenging, especially in long-term prediction. PM2.5 monitoring data comprise a complex time series that contains multiple components with different characteristics; therefore, it is difficult to obtain an accurate prediction by a single model. In this study, an integrated predictor is proposed, in which the original data are decomposed into three components, that is, trend, period, and residual components, and then different sub-predictors including autoregressive integrated moving average (ARIMA) and two gated recurrent units are used to separately predict the different components. Finally, all the predictions from the sub-predictors are combined in fusion node to obtain the final prediction for the original data. The results of predicting the PM2.5 time series for Beijing, China showed that the proposed predictor can effectively improve prediction accuracy for long-term prediction.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Quality Monitoring and Forecasting · Air Quality and Health Impacts · Advanced Chemical Sensor Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China
Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China
Funding
National Natural Science Foundation of China · Beijing Municipal Education Commission
References (56)
Show source-provided references
1. Rybarczyk, Y., and Zalakeviciute, R. (2018). Machine learning approaches for outdoor air quality modelling: A systematic review. Appl. Sci., 8.10.3390/app8122570 ↗
2. Zhang, J., and Ding, W. (2017). Prediction of air pollutants concentration based on an extreme learning machine: The case of Hong Kong. Int. J. Environ. Res. Public Health, 14.10.3390/ijerph14020114 ↗
3. Xu, X., and Ren, W. (2019). Prediction of Air Pollution Concentration Based on mRMR and Echo State Network. Appl. Sci., 9.10.3390/app9091811 ↗
4. Two-stage least squares based iterative estimation algorithm for CARARMA system modeling10.1016/j.apm.2012.10.014 ↗
5. Decomposition based fast least squares algorithm for output error systems10.1016/j.sigpro.2012.12.013 ↗
6. A filtering based multi-innovation extended stochastic gradient algorithm for multivariable control systems10.1007/s12555-016-0081-z ↗
7. Gradient based and least-squares based iterative identification methods for OE and OEMA systems10.1016/j.dsp.2009.10.012 ↗
8. Recursive parameter estimation algorithm for multivariate output-error systems10.1016/j.jfranklin.2018.04.013 ↗
9. Partially coupled gradient estimation algorithm for multivariable equation-error autoregressive moving average systems using the data filtering technique10.1049/iet-cta.2018.5541 ↗
10. Gradient-based and least-squares-based iterative algorithms for Hammerstein systems using the hierarchical identification principle10.1049/iet-cta.2012.0313 ↗
11. Decomposition- and gradient-based iterative identification algorithms for multivariable systems using the multi-innovation theory10.1007/s00034-018-1014-2 ↗
12. State filtering-based least squares parameter estimation for bilinear systems using the hierarchical identification principle10.1049/iet-cta.2018.0156 ↗
13. Highly computationally efficient state filter based on the delta operator10.1002/acs.2995 ↗
14. Relevance analysis and short-term prediction of PM2.5 concentrations in Beijing based on multi-source data10.1016/j.atmosenv.2016.11.054 ↗
15. Wang, W., and Niu, Z. (2009, January 4–5). VAR Model of PM2.5, Weather and Traffic in Los Angeles-Long Beach Area. Proceedings of the 2009 International Conference on Environmental Science and Information Application Technology, Wuhan, China.10.1109/ESIAT.2009.226 ↗
16. Feature functional theory–binding predictor (FFT–BP) for the blind prediction of binding free energies10.1007/s00214-017-2083-1 ↗
17. Zhu, H., and Lu, X. (2016, January 7–9). The prediction of PM2.5 value based on ARMA and improved BP neural network model. Proceedings of the 2016 International Conference on Intelligent Networking and Collaborative Systems, Ostrawva, Czech Republic.10.1109/INCoS.2016.81 ↗
18. Prediction algorithm of PM2.5 mass concentration based on adaptive BP neural network10.1007/s00607-018-0628-3 ↗
19. An improved grey neural network model for predicting transportation disruptions10.1016/j.eswa.2015.09.052 ↗
20. Haiming, Z., and Xiaoxiao, S. (2013, January 29–30). Study on prediction of atmospheric PM2.5 based on RBF neural network. Proceedings of the 2013 Fourth International Conference on Digital Manufacturing & Automation, Qingdao, China.10.1109/ICDMA.2013.306 ↗
21. Impact of land cover changes and climate on the main airborne pollen types in Southern Spain
22. Modeling pollen time series using seasonal-trend decomposition procedure based on LOESS smoothing10.1007/s00484-016-1215-y ↗
23. Analysis of seasonal signals and long-term trends in the height time series of IGS sites in China10.1007/s11430-016-5285-9 ↗
24. Learning representations by back-propagating errors10.1038/323533a0 ↗
25. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
26. Cho, K., Van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25–29). Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Doha, Qatar.10.3115/v1/D14-1179 ↗
27. A deep recurrent neural network for air quality classification
28. Huang, C.J., and Kuo, P.H. (2018). A deep cnn-lstm model for particulate matter (PM2.5) forecasting in smart cities. Sensors, 18.10.3390/s18072220 ↗
29. Pak, U., Ma, J., Ryu, U., Ryom, K., Juhyok, U., Pak, K., and Pak, C. (2019). Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: A case study of Beijing, China. Sci. Total Environ.10.1016/j.scitotenv.2019.07.367 ↗
30. Global and local statistical properties of fixed-length nonparametric smoothers10.1007/BF02509830 ↗
31. STL: A seasonal-trend decomposition procedure based on loess
32. Six-decade temporal change and seasonal decomposition of climate variables in Lake Dianchi watershed (China): Stable trend or abrupt shift10.1007/s00704-014-1098-y ↗
33. Box, G., Gwilym, M., Gregory, C., and Greta, M. (2015). Time Series Analysis: Forecasting and Control, John Wiley & Sons. [1st ed.].
34. A New Look at the Statistical Model Identification10.1109/TAC.1974.1100705 ↗
35. Huang, Q., Wang, W., Zhou, K., You, S., and Neumann, U. (2016). Scene labeling using gated recurrent units with explicit long range conditioning. arXiv.
36. (2017, July 20). Mission China. Available online: http://www.stateair.net/web/historical/1/1.html.
37. Xie, R., Ding, Y., Hao, K., Lei, C., and Tong, W. (2017, January 17–20). Using gated recurrence units neural network for prediction of melt spinning properties. Proceedings of the 2017 11th Asian Control Conference (ASCC), Gold Coast, Australia.10.1109/ASCC.2017.8287531 ↗
38. State estimation for bilinear systems through minimizing the covariance matrix of the state estimation errors10.1002/acs.3027 ↗
39. Ma, H., Pan, J., Ding, F., Xu, L., and Ding, W. (2019). Partially-coupled least squares based iterative parameter estimation for multi-variable output-error-like autoregressive moving average systems. IET Control Theory Appl., 13.10.1049/iet-cta.2019.0112 ↗
40. The filtering-based maximum likelihood iterative estimation algorithms for a special class of nonlinear systems with autoregressive moving average noise using the hierarchical identification principle10.1002/acs.3029 ↗
41. Hierarchical principle-based iterative parameter estimation algorithm for dual-frequency signals10.1007/s00034-018-1015-1 ↗
42. Maximum likelihood recursive identification for the multivariate equation-error autoregressive moving average systems using the data filtering10.1109/ACCESS.2019.2905576 ↗
43. Hierarchical identification for multivariate Hammerstein systems by using the modified Kalman filter10.1049/iet-cta.2016.1033 ↗
44. Filtering-based multistage recursive identification algorithm for an input nonlinear output-error autoregressive system by using the key term separation technique10.1007/s00034-016-0333-4 ↗
45. New gradient based identification methods for multivariate pseudo-linear systems using the multi-innovation and the data filtering10.1016/j.jfranklin.2016.11.025 ↗
46. Decomposition based least squares iterative identification algorithm for multivariate pseudo-linear ARMA systems using the data filtering10.1016/j.jfranklin.2016.11.030 ↗
47. States based iterative parameter estimation for a state space model with multi-state delays using decomposition10.1016/j.sigpro.2014.08.011 ↗
48. State filtering and parameter estimation for linear systems with d-step state-delay10.1049/iet-spr.2013.0076 ↗
49. Combined state and least squares parameter estimation algorithms for dynamic systems10.1016/j.apm.2013.06.007 ↗
50. Coupled-least-squares identification for multivariable systems10.1049/iet-cta.2012.0171 ↗
51. Hierarchical multi-innovation stochastic gradient algorithm for Hammerstein nonlinear system modeling10.1016/j.apm.2012.04.039 ↗
52. An efficient hierarchical identification method for general dual-rate sampled-data systems10.1016/j.automatica.2013.12.025 ↗
53. Partially coupled stochastic gradient identification methods for non-uniformly sampled systems10.1109/TAC.2010.2050713 ↗
54. Hierarchical least squares identification for linear SISO systems with dual-rate sampled-data10.1109/TAC.2011.2158137 ↗
55. Novel data filtering based parameter identification for multiple-input multiple-output systems using the auxiliary model10.1016/j.automatica.2016.05.024 ↗
56. Gradient based and least squares based iterative estimation algorithms for multi-input multi-output systems