Forecasting Air Pollution Concentrations in Iran, Using a Hybrid Model

Document Type : Original Research Paper


Department of Agricultural Economics, Agricultural Faculty, University of Tabriz, Iran


The present study aims at developing a forecasting model to predict the next year’s air pollution concentrations in the atmosphere of Iran. In this regard, it proposes the use of ARIMA, SVR, and TSVR, as well as hybrid ARIMA-SVR and ARIMA-TSVR models, which combined the autoregressive part of the autoregressive integrated moving average (ARIMA) model with the support vector regression technique (ARIMA-SVR). The main concept of generating a hybrid model is to combine different forecasting techniques so as to reduce the time-series forecasting errors. The data used in this study are annual CO2, CO, NOx, SO2, SO3, and SPM concentrations in Iran. According to the results, the ARIMA-TSVR Model is preferable over the other models, having the lowest error value among them which account for 0.0000076, 0.0000065, and 0.0001 for CO2; 0.0000043, 0.0000012, and 0.000022 for NOx; 0.00032, 0.00028., and 0.0012 for SO2; 0.000021, 0.000014, and 0.00038 for CO; 0.0000088, 0.0000005, and 0.00019 for SPM; and 0.000021, 0.000019, and 0.0044 for SO3. Furthermore, the accuracy of all models are checked in case of all pollutants, through RMSE, MAE, and MAPE value, with the results showing that the hybrid ARIMA-TSVR model has also been the best. Generally, results confirm that ARIMA-TSVR can be used satisfactorily to forecast air pollution concentration. Hence, the ARIMA-TSVR model could be employed as a new reliable and accurate data intelligent approach for the next 35 years’ forecasting.


Abdullah Ahmed, R. and Bin Shabri, A. (2014). Daily crude oil price forecasting model using ARIMA, generalized autoregressive conditional heteroscedastic and support vector machines. American Journal of Applied Science., 11(3); 425-432.
Comparison of prediction models for CO2 emission
predict ARIMA
predict SVR
predict TSVR
predict ARIMA-SVR
predict ARIMA-TSVR
Pakrooh, P. and Pishbahar, E.
Adhikari, R. and Argawal, R.k. (2013). An introductory study on time series modelling and forecasting. Cornell University.
Balali Mood, M., Riahi Zanjani, B. and Ghorani Azam, Adel. (2016). Effect of air pollution on human health and practical measures for prevention in Iran. Journal of Research in Medical Sciences., Not mentioned.
Chuentawat, R., Kerdprasop, N. and Kerdprasop, K. (2017). The forecast of PM10 pollution by using a hybrid model. International Journal of Computer and Communication., 6(3); 128-132.
Deo,R. C., AlMusaylh, M.S., Adamowski, J.f. and Yan, L. (2018). Short term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia, Advanced Engineering Informatics., (35); 1-16.
Hassanvand, M.S., Naddafi, K., Yunesian, M. and Momeniha, F. (2012). Health impact assessment of air pollution in megacity of Tehran, Iran. Iranian Journal of Environmental Health Science and Engineering., 9(28);1-7.
Haung, W. (2017). A hybrid ARIMA-SVM algorithm for PM2.5 concentration prediction using binary orthogonal wavelet transformation. Allen Institute for Artificial Intelligence.
He, Y., Zhu, Y. and Duan, D. (2006). Research on hybrid ARIMA and support vector machine model in short term load forecasting. Sixth International Conference on Intelligent Systems Design and Applications.
Hosseini, V. and Shahbazi, H. (2016). Urban air pollution in Iran. Journal of Iranian Study., 49(6); 1029-1046. Hussain, A., Rahman, M. and Alam Memon, J. (2016). Forecasting electricity consumption in Pakistan: the way forward. Energy Policy., (90); 73-80.
Hu, J. and Wang, J. (2015). A robust combination approach for short term wind speed forecasting and analysis: combination of the ARIMA, ELM, SVM and LSSVM forecasts using a GPR model. Energy., (93); 41-56.
Inglesi-Lotz, R., Cowan, Wendy N., Chang, T. and Gupta, R. (2014). The nexus of electricity consumption, economic growth and CO2 emission in the BRICS countries. Energy Policy., (66); 359-368.
Kumar, M. and Thenmozhi, M. (2014). Forecasting stock index returns using ARIMA-SVM, ARIMA-ANN, and ARIMA-random forest hybrid models. International Journal of Banking, Accounting and Finance., 5(3); 284-308.
Liu, Y., Wang, P., Qin, Z. and Zhang, G. (2015). A novel hybrid forecasting model for PM10 and SO2 daily concentration. Science of the Total Environment., (505); 1202-1212.
Lu, W., Wang, W., Leung, A. Y.T., Lo. Y., Richard K.K., Xu, Z. and Fan, H. (2014). Air pollution parameter forecasting using support vector machines. Conference Paper 2002.
Mabahwi, N.A.B., Leh, O.L.H. and Omar, D. (2014). Human health and wellbeing: Human health effect of air pollution. AMER International Conference on Quality of Life The Pacific Sutera Hotel, Malaysia 4-5 January 2014.
Nie, H., Liu, G., Liu, X. and Wang, Y. (2012). Hybrid of ARIMA and SVMs for short term load forecasting, Energy Procedia.. (16); 1455-1460.
Nieto, P.J.G., Sanchez, A.S., Fernandez, P.R., Diaz, J.J.D. and Rodriguez, F.J.I. (2011). Application of an SVM-based regression model to the air quality study at local scale in the Aviles urban area (Spain). Mathematical and Computer Modelling., (54);1453-1466.
Nieto, P.J.G., Lasheras, F.S., Gracia-Gonzalo, E. and Juez, F.J.D. (2011). PM10 concentration forecasting in the metropolitan area of Ovideo using models based on SVM, MLP, VARMA, ARIMA: A case study. Science of the Total Environment., (621); 753-761.
Noori, R., Moazami, S., Jabbarian Amiri, B., Yeganeh, B., Partani, S. and Safavi, S. 2015. Reliable prediction of carbon monoxide using developed support vector machine, Atmospheric Pollution Research., 1-7.
Pai, P.F. and Lin, Ch.Sh. (2005). A hybrid ARIMA and support vector machines model in stock price forecasting. Omega., (33); 497-505.
Pao, H.T. and Tsai, Ch.M. (2011). Modelling and forecasting the CO2 emissions, energy consumption and economic growth in Brazil. Energy., (36); 2450-2458.
Pokora, J. (2017). Hybrid ARIMA and support vector regression in short term electricity price forecasting. Acta Universitatis Agriculturate et Silviculturae Mendelianae Brunenis., 65(2); 699-708.
Sahoo, B., Bhusan. Jha, R., Singh, A., and Kumar, D. 2018. Application of support vector regression for modeling low flow Time series, Water Resources and Hydrologic Engineering., 1-12.
Statistical Center of Iran, (2016).
Saleh, Ch., Dzakiyullah, N.R. and Nugroho, Jonathan Bayu. (2015). Carbon dioxid emission prediction using support vector machine, Materials Science and Engineering Conferences.
Pollution, 5(4): 739-747, Autumn 2019
Pollution is licensed under a "Creative Commons Attribution 4.0 International (CC-BY 4.0)"
Sen, P., Roy, M. and Pal, P. (2016). Application of Arima for forecasting energy consumption and GHG emission: A case study of an Indian pig iron manufacturing. Energy., (116); 1031-1038.
Sujjaviriyasup, Th. and Pitiruek, K. (2013). Hybrid ARIMA-support vector machine model for agricultural production planning. Applied Mathematical Science., 7(57); 2833-2840.
Vong, Ch.M., Ip, W.F., Wong, Pak-kin. and Yang, J. (2012). Short term prediction of air pollution in Mcau using support vector machines. Journal of Control Science and Engineering., (2012); 1-11.
Yang, Ch.Y., Tsai, Sh.Sh., Goggins, W. B. and Chiu, H.F. (2003). Evidence for an association between air pollution and daily stroke admissions in Kaohsiung Taiwan. Stroke., 2003 (34); 2612-2626.
Zaim, S., Ogcu, G. and Demirel, O. (2012). Forecasting electricity consumption with neural networks and support vector regression. social and Behavioral Science., 58; 1576-1585.
Zhang, J. and Ding, W. (2017). Prediction of air pollutants concentration based on an extreme learning machine: The case of Hong Kong. International Journal of Environmental Research and Public Health., 14(114); 1-19.
Zhang, H. Wang, P. Qin, Z. and Zhang, G. (2017). A novel hybrid GARCH model based on ARIMA and SVM for PM2.5 concentration forecasting, Atmospheric Pollution Research., 1-11.
Zhu, B. and Wei, Y. (2013). Carbon price forecasting with a novel hybrid ARIMA and least squares support vector machines methodology. Omega., (41); 517-524.