Tropospheric ozone is a standard air pollutant, and can adversely affect human respiratory system. Many metropolitan areas around the world struggle to meet ozone standards. Therefore, timely and effective ozone prediction can help regulatory agencies to prevent the harm to human body and environment induced by excessive ozone concentration in advance. For selecting the optimal individual model set in combined forecasting, this research proposes CEEMD-Subset-OASVR-GRNN model, based on complete ensemble empirical mode decomposition (CEEMD) method, support vector regression (SVR), generalized regression neural network (GRNN) and optimization algorithms (OA), to predict the daily average concentration of ozone. Specifically, for the ozone time series, CEEMD is used to decompose the original data into three intrinsic mode functions (IMFS), PSO-SVR, PSOGSA-SVR, GWO-SVR and GRNN are employed to model and predict the IMFS, and the prediction results are randomly combined to establish 100 individual models (appendix Table A1). The selection methods of the individual models include MSE ranking, factor score and unsupervised learning systematic clustering, and the influence of number of individual models on combined forecasting is studied. The ozone series of two very distinct Chinese metropolitan areas, Xiamen and Harbin, are selected as the experimental data. The prediction results show that the systematic clustering method is helpful for effectively improving the prediction accuracy of the combined model.
Al-Alawi, S.M., Abdul-Wahab, S.A., Bakheit, C.S., 2008. Combining principal component regression and artificial neural networks for more accurate predictions of groundlevel ozone. Environ. Model. Softw 23 (4), 396–403.
Breiman, L., 1996. Stacked regressions. Mach. Learn. 24 (1), 49–64. Bunn, D.W., 1975. A Bayesian approach to the linear combination of forecasts. J. Oper. Res. Soc. 26 (2), 325–329.
Brandt, J., Christensen, J.H., Frohn, L.M., Palmgren, F., Berkowicz, R., Zlatev, Z., 2001. Operational air pollution forecasts from European to local scale. Atmos. Environ. 35, S91–S98.
Bates, J.M., Granger, C.W.J., 1969. The combination of forecasts. J. Oper. Res. Soc. 20 (4), 451–468.
Celikoglu, H.B., Cigizoglu, H.K., 2007. Public transportation trip flow modeling with generalized regression neural networks. Adv. Eng. Software 38 (2), 71–79.
Chen, G.J., Li, K.K., Chung, T.S., Sun, H.B., Tang, G.Q., 2001. Application of an innovative combined forecasting method in power system load forecasting. Electr. Power Syst. Res. 59 (2), 131–137.
Chan, F., Pauwels, L.L., 2018. Some theoretical results on forecast combinations. Int. J. Forecast. 34 (1), 64–74.
Cheng, G., Yang, Y., 2015. Forecast combination with outlier protection. Int. J. Forecast. 31 (2), 223–237.
Durao, R.M., Mendes, M.T., Joao Pereira, M., 2016. Forecasting O-3 levels in industrial area surroundings up to 24 h in advance, combining classification trees and MLP models. Atmos. Poll. Res. 7 (6), 961–970.
Fei, S.W., Liu, C.L., Miao, Y.B., 2009. Support vector machine with genetic algorithm for forecasting of key-gas ratios in oil-immersed transformer. Expert Syst. Appl. 36 (3), 6326–6331.
Feng, Y., Zhang, W.F., Sun, D.Z., Zhang, L.Q., 2011. Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification. Atmos. Environ. 45 (11), 1979–1985.
Granger, C.W.J., 1989. Combining forecasts-twenty years later. J. Forecast. 8 (3), 167–173.
Granger, C., Newbold, P., 1974. Spurious regressions in econometrics. J. Econom. 2 (2), 111–120.
Haidar, A.M.A., Mustafa, M.W., Ibrahim, F.A.F., Ahmed, I.A., 2011. Transient stability evaluation of electrical power system using generalized regression neural networks. Appl. Soft Comput. 11 (4), 3558–3570.
Hoeting, J.A., Madigan, D., Raftery, A.E., Volinsky, C.T., 1999. Bayesian model averaging: a tutorial. Stat. Sci. 14 (4), 382–401.
He, Y.Y., Yan, Y.D., Xu, Q.F., 2019. Wind and solar power probability density prediction via fuzzy information granulation and support vector quantile regression. Int. J. Electr. Power Energy Syst. 113, 515–527.
Isukapalli, S.S., 1999. Uncertainty analysis of transport-transformation models. Diss. Theses-Gradworks 57 (1), 31–32.
Kang, H., 1986. Unstable weights in the combination of forecasts. Manag. Sci. 32 (6), 683–695.
Kennedy, J., Eberhart, R., 1995. Particle swarm optimization. Neural Netw. 4, 1942–1948.
Kumar, A., Goyal, P., 2011. Forecasting of daily air quality index in Delhi. Sci. Total Environ. 409 (24), 5517–5523.
Kurt, A., Gulbagci, B., Karaca, F., Alagha, O., 2008. An online air pollution forecasting system using neural networks. Environ. Int. 34 (5), 592–598.
Lemke, C., Gabrys, B., 2010. Meta-learning for time series forecasting and forecast combination. Neurocomputing 73 (10–12), 2006–2016.
Li, H.Z., Guo, S., Li, C.J., Sun, J.Q., 2013. A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm. Knowl. Based Syst. 37, 378–387.
Lzadyar, N., Ghadamian, H., Ong, H.C., Moghadam, Z., Tong, C.W., Shamshirband, S., 2015. Appraisal of the support vector machine to forecast residential heating demand for the District Heating System based on the monthly overall natural gas consumption. Energy 93, 1558–1567.
Li, X.L., Luo, A.R., Li, J.G., Li, Y., 2019. Air pollutant concentration forecast based on support vector regression and quantum-behaved particle swarm optimization. Environ. Model. Assess. 24 (2), 205–222.
Liu, X.L., Moreno, B., Salome Garcia, A., 2016. A grey neural network and input-output combined forecasting model. Primary energy consumption forecasts in Spanish economic sectors. Energy 115, 1042–1054.
Luna, A.S., Paredes, M.L.L., de Oliveira, G.G.G., Correa, S.M., 2014. Prediction of ozone concentration in tropospheric levels using artificial neural networks and support vector machine at Rio de Janeiro, Brazil. Atmos. Environ. 98, 98–104.
LeBlanc, M., Tibshirani, R., 1996. Combining estimates in regression and classification. J. Am. Stat. Assoc. 91 (436), 1641–1650.
Mirjalili, S., Hashim, S.Z.M., 2010. A new hybrid PSOGSA algorithm for function optimization. IEEE. Paper presented at the 2010 International Conference on Computer and Information Application. pp. 374–377.
Martin, B., Marot, J., Bourennane, S., 2019. Mixed grey wolf optimizer for the joint denoising and unmixing of multispectral images. Appl. Soft Comput. 74, 385–410.
Mirjalili, S., Mirjalili, S.M., Lewis, A., 2014. Grey wolf optimizer. Adv. Eng. Software 69, 46–61.
Perez, P., 2012. Combined model for PM10 forecasting in a large city. Atmos. Environ. 60, 271–276.
Reichert, P., Borsuk, M.E., 2005. Does high forecast uncertainty preclude effective decision support. Environ. Model. Softw 20 (8), 991–1001.
Rashedi, E., Nezamabadi-pour, H., Saryazdi, S., 2009. GSA: a gravitational search algorithm. Inf. Sci. 179 (13), 2232–2248.
Specht, D.F., 1993. The general regression neural network—Rediscovered. Neural Netw. 6 (7), 1033–1034.
Shen, S.J., Li, G., Song, H.Y., 2011. Combination forecasts of International tourism demand. Ann. Tourism Res. 38 (1), 72–89.
Sharma, P., Sundaram, S., Sharma, M., Sharma, A., Gupta, D., 2019. Diagnosis of Parkinson's disease using modified grey wolf optimization. Cogn. Syst. Res. 54, 100–115.
Tripathi, A.K., Sharma, K., Bala, M., 2018. A novel clustering method using enhanced grey wolf optimizer and MapReduce. Big Data Res. 14, 93–100.
Vapnik, V.N., 1999. An overview of statistical learning theory. IEEE Trans. Neural Netw. 10 (5), 988–999.
Valuntaite, V., Girgzdiene, R., 2015. Outdoor and indoor ozone level – a potential impact on human health. Vojnosanit. Pregl. 72 (8), 696–701.
Wiwatanadate, P., 2014. Acute air pollution-related symptoms among residents in chiang mai, Thailand. J. Environ. Health 76 (6), 76–84.
Wang, Q., Li, S.Y., Li, R.R., 2019. Will Trump's coal revival plan work? - comparison of results based on the optimal combined forecasting technique and an extended IPAT forecasting technique. Energy 169, 762–775.
Westerlund, J., Urbain, J.P., Bonilla, J., 2014. Application of air quality combination forecasting to bogota. Atmos. Environ. 89, 22–28.
Xiao, L., Wang, J.Z., Dong, Y., Wu, J., 2015. Combined forecasting models for wind energy forecasting: a case study in China. Renew. Sustain. Energy Rev. 44, 271–288.
Xie, R., Zhao, G.M., Zhu, B.Z., Chevallier, J., 2018. Examining the factors affecting air pollution emission growth in China. Environ. Model. Assess. 23 (4), 389–400.
Yeh, J.R., Shieh, J.S., Huang, N.E., 2010. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method. Adv. Adapt. Data Anal. 2, 135–156.
Yang, Z.S., Wang, J., 2018. A combination forecasting approach applied in multistep wind speed forecasting based on a data processing strategy and an optimized artificial intelligence algorithm. Appl. Energy 230, 1108–1125.
Zendehboudi, A., Baseer, M.A., Saidur, R., 2018. Application of support vector machine models for forecasting solar and wind energy resources: a review. J. Clean. Prod. 199, 272–285.
Zhang, X., Chen, M.Y., Wang, M.G., Ge, Y.E., Stanley, H.E., 2019. A novel hybrid approach to Baltic Dry Index forecasting based on a combined dynamic fluctuation network and artificial intelligence method. Appl. Math. Comput. 361, 499–516.
Zhou, Q.O., Jiang, H.Y., Wang, J.Z., Zhou, J.L., 2014. A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network. Sci. Total Environ. 496, 264–274.
Zhu, S.L., Lian, X.Y., Liu, H.X., Hu, J.M., Wang, Y.Y., 2017. Daily air quality index forecasting with hybrid models: a case in China. Environ. Pollut. 231, 1232–1244. Zou, H., Yang, Y., 2004. Combining time series models for forecasting. Int. J. Forecast. 20 (1), 69–84.
Zhu, S.L., Yang, L., Wang, W.N., Liu, X.R., Lu, M.M., Shen, X.P., 2018. Optimal-combined model for air quality index forecasting: 5 cities in North China. Environ. Pollut. 243, 842–850.