Comparison of Prediction Models (ANN and Time Series) for Studying the Dispersion of Pollutants (SOx, NOx and Particulate Matter) from Vehicular Emissions – A Case Study

IJEP 43(5): 409-420 : Vol. 43 Issue. 5 (May 2023)

Ram Kishor Singh and Bindhu Lal*

Birla Institute of Technology, Ranchi, Jharkhand – 835 215, India


Pollution due to vehicular emissions is increasing day by day due to changes in economic conditions and lifestyle of people. Ranchi, the capital of newly developed state of Jharkhand, has seen a lot of infrastructural development which led to an increase in the number of vehicles and hence increased vehicular pollution. A study is made to predict concentrations of SOx, NOx and particulate matter from vehicular emission using intelligent models (ANN, time series) in Ranchi city. Comparisons are made between observed values and predicted values of the above models. The prediction accuracy of models is tested using statistical parameters (index of agreement (d), model bias (MB), fractional bias (FB), normalised mean square error (NMSE) and correlation coefficient (R) and it is seen that predictions are correct and the concentrations predicted by models are comparable to observed values. Thus, the accuracy of the predictions using above models is established in this study.


Feed forward neural network, Time series, Statistical parameters, SOx, NOx, Particulate matter


  1. Ghose, M.K., R. Paul and S.K. Banerjee. 2004. Assessment of the impacts of vehicular emissions in urban air quality and its managements in Indian context : The case of Kolkata (Calcutta). Env. Sci. Policy. 7(4):345-351.
  2. Winkler, S.L., J.E. Anderson and L. Garza. 2018. Vehicle criteria pollutant (PM, NOx, CO, HCs) emissions: How low should we go? NPJ Clim. Atmos. Sci., 1:26.
  3. Kheirbek, I., et al. 2016. The contribution of motor vehicle emissions to ambient fine particulate matter public health impacts in New York city : A health burden assessment. Env. Health. 15:89.
  4. Chetana, K. and K. Sharda. 2014. A review of vehicular pollution in urban India and its effects on human health. J. Adv. Laboratory Res. Biol., 5(3):54-61.
  5. Elangasinghe, M.A., et al. 2014. Development of an ANN-based air pollution forecasting system with explicit knowledge through sensitivity analysis. Atmos. Poll. Res., 5:696-708.
  6. Hossain, K.M.A. 2014. Predictive ability of improved neural network models to simulate pollutant dispersion. Int. J. Atmos. Sci.,141923:1-12.
  7. Goulier, L., et al. 2020. Modelling of urban air pollutant concentrations with artificial neural networks using novel input variables. Int. J. Env. Res. Public Health. 17(6):2025.
  8. Kachba, Y., et al. 2020. Artificial neural networks to estimate the influence of vehicular emission variables on morbidity and mortality in the largest metropolis in South America. Sustain., 12(7):2621.
  9. Sekhar, C., et al. 2016. Potential assessment of neural network and decision tree algorithms for forecasting ambient PM2.5and concentrations : Case study. J. Hazard. Toxic Radioactive Waste. 20 (4).
  10. Salcedo, R.L.R., et al. 1999. Time series analysis of air pollution data. Atmos. Env., 33:2361-2372.
  11. Pan, A., S.E. Sarnat and H.H. Chang. 2018. Time series analysis of air pollution and health accounting for covariate dependent over dispersion. American J. Epidemiol., 187(12):2698-2704.
  12. Espinosa, R., et al. 2021. A time series forecasting based multicriteria methodology for air quality prediction. Appl. Soft Computing. 113:107850.
  13. Hota, H.S., R. Handa and A.K. Srivas. 2017. Time series data prediction using sliding window-based RBF neural network. Int. J. Computational Intelligence Res., 13(5):1145-1156.
  14. Samal, K.K.R., et al. 2019. Time series based air pollution forecasting using SARIMA and PROPHET model. International Conference on Information technology and Computer Communications (ITCC 2019). Proceedings, pp 80-85.
  15. Kumar, A. and P. Goyal. 2011. Forecasting of air quality in Delhi using principal component regression technique. Atmos. Poll. Res., 2(4):436-444.
  16. Kumar, S., S. Mishra and S.K. Singh. 2020. A machine learning based model to estimate PM2.5concentration level in Delhi city. Heliyon. 6(11): e05618.
  17. Alyousifi, Y., et al. 2021. A new hybrid fuzzy time series model with an application to predict PM10concentration. Ecotoxicol. Env. Safety. 227 (112875): 1-8.
  18. Wang, D. and W.Z. Lu. 2006. Forecasting of ozone layer in time series using MLP model with a novel hybrid training algorithm. Atmos. Env., 40(5):913-924.
  19. Abbood, Z.M., O.T. Al-Taai and W.G. Nassif. 2021. Impact of wind speed and direction on low cloud cover over Baghdad city. Current Appl. Sci. Tech., 21(3):590-600.
  20. Sarkar, R., et al. 2019. A comparative study of activation functions of NAR and NARX neural network for long-term wind speed forecasting in Malaysia. Mathematical Problems Eng. DOI: 10.1155/2019/ 6403081.
  21. Musa, R.M., et al. 2019. Psychological variables in ascertaining potential archers: Identifying potential archers. In Machine learning in sports. Springer Briefs Appl. Sci. Tech., pp 21-27.
  22. Guerneccia, C., et al. 2018. ARIMA model application to air pollution data in Monterrey, Mexico. AIP Conference Proceedings, 1982, 02004.
  23. Asklany, S., W. Mansouri and S. Othmen. 2019. Levenberg-Marquardt deep learning algorithm for sulphur dioxide prediction. Int. J. Computer Sci. Network Security. 19(12): 7-12.
  24. Lal, B. and S.K. Tripathy. 2012. Prediction of dust concentration in open cast coal mine using artificial neural network. Atmos. Poll. Res., 3:211-218.