A hybrid model for online prediction of PM2:5 concentration: A case study

Document Type : Article


1 Department of Industrial Engineering, Ferdowsi University of Mashhad, Mashhad, Iran

2 Environmental Pollution Monitoring Center of Mashhad, Deputy of Services, and Urban Environment, Municipality of Mashhad, Iran


In this paper, we aim at developing a model to predict the daily average concentration of particulate matters with a diameter of less than 2.5 micrometers (PM2.5). In the introduced model, we incorporate Weather Research and Forecasting (WRF) meteorological model, Monte Carlo simulation, wavelet transform, and multilayer perceptron (MLP) neural networks. In particular, the MLP and wavelet transformation are combined for prediction. In order to predict the model’s input parameters, including wind speed, wind direction, temperature, rainfall, and temperature inversion, the WRF meteorological model is used. Finally, according to the available uncertainty in the input data and in order to achieve a more accurate prediction, the Monte Carlo simulation is utilized. In order to assess the effectiveness of the model in the real world, it has been conducted in an online mode for 35 days. Numerical results give an acceptable accuracy in terms of some widely used measures. In particular, taking into account the R measurements, it is equal to 0.831 over the set of test instances.


Main Subjects

[1]    Molina, M.J. and Molina, L.T. “Megacities and atmospheric pollution”,Air. Waste. Manag. Assoc., 54, pp. 644-680 (2004).
[2]    Kolehmainen, M., Martikainen, H. and Ruuskanen, J. “Neural networks and periodic components used in air quality forecasting”,Atmos. Environ., 35, pp. 815-825(2001).
[3]    Zhang, Y., Bocquet, M., Mallet, V. and et al. “Real-time air quality forecasting, part I: History, techniques, and current status”,Atmos. Environ., 60, pp. 632-655 (2012).
[4]    U.S. EPA.“Guidelines for developing an air quality (Ozone and PM2.5) forecasting program”, U.S. Environmental Protection Agency, Office of Air Quality Planning and Standards, Research Triangle Park, North Carolina. EPA-456/R- 03-002 (2003).
[5]    Feng, X., Li, Q., Zhu, Y. and et al.“Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation”,Atmos. Environ., 107, pp. 118-128 (2015).
[6]    Hrust, L., Klaić, Z.B., Križan, J. and et al. “Neural network forecasting of air pollutants hourly concentrations using optimised temporal averages of meteorological variables and pollutant concentrations”,Atmos. Environ., 43, pp. 5588-5596 (2009).
[7]    Perez, P. and Gramsch, E. “Forecasting hourly PM2.5 in Santiago de Chile with emphasis on night episodes”,Atmos. Environ., 124, pp. 22-27 (2016).
[8]    Donnelly, A., Naughton, O., Broderick, B. and et al. “Short-Term Forecasting of Nitrogen Dioxide (NO2) Levels Using a Hybrid Statistical and Air Mass History Modelling Approach”,Environ. Model.Assess., 22, pp. 231-241 (2016).
[9]    Fernando, H.J.S., Mammarella, M.C., Grandoni, G. and et al. “Forecasting PM10 in metropolitan areas: efficacy of neural networks”,Environ. Pollut., 163, pp. 62-67 (2012).
[10]    Genc, D.D., Yesilyurt, C. and Tuncel, G. “Air pollution forecasting in Ankara, Turkey using air pollution index and its relation to assimilative capacity of the atmosphere”,Environ. Monit Assess., 166, pp. 11-27 (2010).
[11]    Vlachogianni, A., Kassomenos, P., Karppinen, A. and et al. “Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki”,Sci. Total. Environ., 409, pp. 1559-1571 (2011).
[12]    Perez, P. and Reyes, J. “An integrated neural network model for PM10 forecasting”,Atmos. Environ., 40, pp. 2845-2851 (2006).
[13]    Arhami, M., Kamali, N. and Rajabi, M.M. “Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations”,Environ. Sci. Pollut. Res.,20, pp. 4777-4789 (2013).
[14]    Osowski, S. and Garanty, K. “Forecasting of the daily meteorological pollution using wavelets and support vector machine”,Eng. Appl. Artif. Intell., 20, pp. 745-755 (2007).
[15]    Luna, A.S., Paredes, M.L.L., de Oliveira, G.C.G. and et al. “Prediction of ozone concentration in tropospheric levels using artificial neural networks and support vector machine at Rio de Janeiro, Brazil”, Atmos. Environ., 98, pp. 98-104 (2014).
[16]    Brunelli, U., Piazza, V., Pignato, L. and et al. “Two-days ahead prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the urban area of Palermo, Italy”,Atmos. Environ., 41, pp. 2967-2995 (2007).
[17]    Boznar, M., Lesjak, M. and Mlakar, P. “A neural network-based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain”,Atmos. Environ. 27B(2), pp. 221-230 (1993).
[18]    Perez, P. and Reyes, J. “Prediction of maximum of 24-h average of PM10 concentrations 30h in advance in Santiago, Chile”,Atmos. Environ., 36, pp. 4555-4561 (2002).
[19]    Jiang, D., Zhang, Y., Hu, X. and et al. “Progress in developing an ANN model for air pollution index forecast”,Atmos. Environ., 38, pp. 7055-7064 (2004).
[20]    Lu, H.C., Hsieh, J.C. and Chang, T.S. “Prediction of daily maximum ozone concentrations from meteorological conditions using a two-stage neural network”,Atmos. Res., 81, pp. 124-139 (2006).
[21]    Paschalidou, A.K., Karakitsios, S., Kleanthous, S. and et al. “Forecasting hourly PM10 concentration in Cyprus through artificial neural networks and multiple regression models: implications to local environmental management”,Environ. Sci. Pollut. Res., 18, pp. 316-327 (2011).
[22]    Wang, P., Liu, Y., Qin, Z. and et al. “A novel hybrid forecasting model for PM10 and SO2 daily concentrations”, Sci. Total. Environ., 505, pp. 1202-1212 (2015).
[23]    Gao, M., Yin, L. and Ning, J. “Artificial neural network model for ozone concentration estimation and Monte Carlo analysis”, Atmos. Environ., 184, pp. 129-139 (2018).
[24]    Siwek, K. and Osowski, S. “Improving the accuracy of prediction of PM10 pollution by the wavelet transformation and an ensemble of neural predictors”,Eng. Appl. Artif. Intell., 25, pp. 1246-1258 (2012).
[25]    Bai, Y., Li, Y., Wang, X. and et al. “Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions”,Atmos. Pollu. Res.,7, pp. 557-566 (2016).
[26]    Bidokhti, A.A., Shariepour, Z. and Sehatkashani, S. “Some resilient aspects of urban areas to air pollution and climate change, case study: Tehran, Iran”, Scientica Iranica A, 23(5), pp. 1994-2004 (2016).
[27]    http://www.razavimet.ir
[28]    http://www.scats.com.au
[29]    http://www.weather.uwyo.edu
[30]    http://www.raob.com
[31]    http://www.epmc.mashhad.ir
[32]    Misiti, M., Misiti, Y., Oppenheim, G. and et al. “Wavelet Toolbox”, pp. 1-16_1-23, MathWorks, Natick (1996).
[33]    Mallat, S.“A theory for multiresolution signal decomposition: The wavelet representation”, IEEE Transactions PAMI, 11, pp. 674–693 (1989).
[34]    User’s Guide for the Advanced Research WRF (ARW) Modeling System Version 3.9. Available online: http://www.mmm.ucar.edu/wrf/users/docs/user_guide_V3/contents.html (accessed 2017). 
[35]    Bouloukza, I., Mourad, M., Medoued, A. and et al. “Multi-objective optimization design and performance evaluation of slotted Halbach PMSM using Monte Carlo method”, Scientica Iranica D, 25(3), pp. 1533-1544 (2018).
[36]    Sarle, W.S. “Stopped training and other remedies for overfitting”, Proceedings of the 27th Symposium on the Interface of Computer Science and Statistics, pp. 352-360 (1995).
[37]    Kurt, A. and Oktay, A.B. “Forecasting air pollutant indicator levels with geographic models 3days in advance using neural networks”,Expert. Syst. with Appl., 37, pp. 7986-7992 (2010).
[38]    Domańska, D. and Wojtylak, M.“Explorative forecasting of air pollution”,Atmos. Environ., 92, pp. 19-30 (2014).