An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting

Chemosphere

Volumn 222, Issue , 2019, Pages 286-294

  Bai, Yun ^a   Zeng, Bo ^a   Li, Chuan ^a   Zhang, Jin ^b  

^a CHONGQING TECHNOLOGY AND BUSINESS UNIVERSITY   (China)

^b JINAN UNIVERSITY   (China)

Author keywords

Ensemble learning; Forecasting; Long short term memory; Mode transformation; PM2.5 concentrations

Indexed keywords

BRAIN; FEEDFORWARD NEURAL NETWORKS; FORECASTING; INVERSE PROBLEMS; LEARNING SYSTEMS; MEAN SQUARE ERROR;

ENSEMBLE EMPIRICAL MODE DECOMPOSITIONS (EEMD); ENSEMBLE LEARNING; ENVIRONMENTAL MONITORING; MEAN ABSOLUTE PERCENTAGE ERROR; METEOROLOGICAL VARIABLES; MODE TRANSFORMATION; PM2.5 CONCENTRATION; ROOT MEAN SQUARE ERRORS;

LONG SHORT-TERM MEMORY;

CONCENTRATION (COMPOSITION); DATA SET; DECOMPOSITION; ENSEMBLE FORECASTING; ENVIRONMENTAL MONITORING; MEMORY; PARTICULATE MATTER; PERFORMANCE ASSESSMENT; PUBLIC HEALTH; TRANSFORMATION;

ARTICLE; CHINA; CORRELATION COEFFICIENT; DECOMPOSITION; ENVIRONMENTAL MONITORING; FEATURE EXTRACTION; FORECASTING; LEARNING; SHORT TERM MEMORY; ANALYSIS; ARTIFICIAL NEURAL NETWORK; INFORMATION PROCESSING; PARTICULATE MATTER; PROCEDURES;

BEIJING [CHINA]; CHINA;

BEIJING; CHINA; DATASETS AS TOPIC; ENVIRONMENTAL MONITORING; FORECASTING; MEMORY, SHORT-TERM; NEURAL NETWORKS (COMPUTER); PARTICULATE MATTER;

EID: 85060908111     PISSN: 00456535     EISSN: 18791298     Source Type: Journal    
DOI: 10.1016/j.chemosphere.2019.01.121     Document Type: Article

References (34)

1. Antanasijević D.Z., Ristić M., Perić-Grujić A., Pocajt, V., Forecasting human exposure to PM10 at the national level using an artificial neural network approach. J. Chemom. 27 (2012), 170–177.
2. Bai, Y., Chen, Z.Q., Xie, J., Li, C., Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models. J. Hydrol. 532 (2016), 193–206.
3. Bai, Y., Li, Y., Wang, X., Xie, J., Li, C., Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions. Atmos. Pollut. Res. 7:3 (2016), 557–566.
4. Bas, M.D.C., Ortiz, J., Ballesteros, L., Martorell, S., Evaluation of a multiple linear regression model and SARIMA model in forecasting 7Be air concentrations. Chemosphere 177 (2017), 326–333.
5. Biancofiore, F., Busilacchio, M., Verdecchia, M., Tomassetti, B., Aruffo, E., Bianco, S., Tommaso, S., Colangeli, C., Rosatelli, G., Carlo, P., Recursive neural network model for analysis and forecast of PM10 and PM2.5. Atmos. Pollut. Res. 8:4 (2017), 652–659.
6. Cohen, A.J., Ross Anderson, H., Ostro, B., Pandey, K.D., Krzyzanowski, M., Künzli, N., Gutschmidt, K., Pope, A., Romieu, I., Samet, J.M., Smith, K., The global burden of disease due to outdoor air pollution. J. Toxicol. Environ. Health 68:13–14 (2005), 1301–1307.
7. Dimitriou, K., Kassomenos, P., A study on the reconstitution of daily PM10 and PM2.5 levels in Paris with a multivariate linear regression model. Atmos. Environ. 98 (2014), 648–654.
8. Feng, X., Li, Q., Zhu, Y., Hou, J., Jin, L., Wang, J., Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation. Atmos. Environ. 107 (2015), 118–128.
9. Fu, M., Wang, W., Le, Z., Khorram, M., Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model. Neural Comput. Appl. 26:8 (2015), 1789–1797.
10. Gers, F.A., Schmidhuber, J., Cummins, F., Learning to forget: continual prediction with LSTM. Neural Comput. 12:10 (2000), 2451–2471.
11. Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B., Schmidhuber, J., LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28:10 (2016), 2222–2232.
12. Huang, C.J., Kuo, P.H., A deep CNN-LSTM model for particulate matter (PM2.5) forecasting in smart cities. Sensors, 18(7), 2018, 2220.
13. Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, E.H., Zheng, Q., Tung, C.C., Liu, H.H., The empirical mode decomposition method and the Hilbert spectrum for non-stationary time series analysis. Proc. Roy. Soc. London Ser. A 454 (1998), 903–995.
14. Jian, L., Zhao, Y., Zhu, Y.P., Zhang, M., Bertolatti, D., An application of ARIMA model to predict submicron particle concentrations from meteorological factors at a busy roadside in Hangzhou, China. Sci. Total Environ. 426 (2012), 336–345.
15. Li, C., Tao, Y., Ao, W.G., Yang, S., Bai, Y., Improving forecasting accuracy of daily enterprise electricity consumption using random forest based on ensemble empirical mode decomposition. Energy 165 (2018), 1220–1227.
16. Liu, D., Li, L., Application study of comprehensive forecasting model based on Entropy weighting method on trend of PM2.5 concentration in Guangzhou, China. Int. J. Environ. Res. Publ. Health 12:6 (2015), 7085–7099.
17. Liu, Y., He, K., Li, S., Wang, Z., Christiani, D., Koutrakis, P., A statistical model to evaluate the effectiveness of PM2.5 emissions control during the Beijing 2008 Olympic Games. Environ. Int. 44 (2012), 100–105.
18. Li, X., Peng, L., Yao, X., Cui, S., Hu, Y., You, C., Chi, T., Long short-term memory neural network for air pollutant concentration predictions: method development and evaluation. Environ. Pollut. 231 (2017), 997–1004.
19. Maclin, R., Opitz, D., Popular ensemble methods: an empirical study. J. Artif. Intell. Res. 11 (1999), 169–198.
20. Moisan, S., Herrera, R., Clements, A., A dynamic multiple equation approach for forecasting PM2.5 pollution in Santiago, Chile. Int. J. Forecast. 34 (2018), 566–581.
21. Ong, B.T., Sugiura, K., Zettsu, K., Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5. Neural Comput. Appl. 27:6 (2016), 1553–1566.
22. Rahman, N.H.A., Lee, M.H., Suhartono, Latif, M., Artificial neural networks and fuzzy time series forecasting: an application to air quality. Qual. Quantity 49:6 (2015), 2633–2647.
23. Rokach, L., Ensemble-based classifiers. Artif. Intell. Rev. 33:1–2 (2010), 1–39.
24. Russo, A., Soares, A.O., Hybrid model for urban air pollution forecasting: a stochastic spatio-temporal approach. Math. Geosci. 46 (2014), 75–93.
25. Saide, P., Mena, M., Tolvett, S., Hernandez, P., Carmichael, G., Air quality forecasting for winter-time PM2.5 episodes occurring in multiple cities in central and southern Chile. J. Geophys. Res. Atmos. 121:1 (2016), 558–575.
26. Wang, P., Zhang, H., Qin, Z., Zhang, G., A novel hybrid-Garch model based on ARIMA and SVM for PM2.5 concentrations forecasting. Atmos. Pollut. Res. 8:5 (2017), 850–860.
27. Wang, Y., Wang, H., Chang, S., Avram, A., Prediction of daily PM2.5 concentration in China using partial differential equations. PLoS One, 13(6), 2018, e0197666.
28. Wu, S., Feng, Q., Du, Y., Li, X., Artificial neural network models for daily PM10 air pollution index prediction in the urban area of Wuhan, China. Environ. Eng. Sci. 28 (2011), 357–363.
29. Wu, S.W., Yang, D., Wei, H.Y., Wang, B., Huang, J., Li, H., Shima, M., Deng, F., Guo, X., Association of chemical constituents and pollution sources of ambient fine particulate air pollution and biomarkers of oxidative stress associated with atherosclerosis: a panel study among young adults in Beijing, China. Chemosphere 135 (2015), 347–353.
30. Wu, Z.H., Huang, N.E., Ensemble empirical mode decomposition: a noise assisted data analysis method. Adv. Adapt. Data Anal. 1:1 (2009), 1–41.
31. Xie, J.J., Wang, X., Liu, Y., Bai, Y., Auto encoder-based deep belief regression network for air particulate matter concentration forecasting. J. Intell. Fuzzy Syst. 34:6 (2018), 3475–3486.
32. Yao, Y., Sfarra, S., Ibarra-Castanedo, C., You, R.C., Maldague, X.P.V., The multi-dimensional ensemble empirical mode decomposition. J. Therm. Anal. Calorim. 128:3 (2017), 1841–1858.
33. Yeganeh, B., Hewson, M.G., Clifford, S., Tavassoli, A., Knibbs, L., Morawska, L., Estimating the spatiotemporal variation of NO2 concentration using an adaptive neuro-fuzzy inference system. Environ. Model. Softw 100 (2018), 222–235.
34. Zhu, S., Lian, X., Lin, W., Chen, J., Shen, X., Yang, L., Qiu, X., Liu, X., Gao, W., Ren, X., Li, J., PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors. Atmos. Environ. 183 (2018), 20–32.