Environmental Monitoring and Assessment

, Volume 112, Issue 1–3, pp 327–345 | Cite as

Estimating Air Quality in a Traffic Tunnel Using a Forecasting Combination Model

  • Cheng-Chung Lee
  • Terng-Jou Wan
  • Chao-Yin Kuo
  • Chung-Yi Chung


This study compared three forecasting methods based on their accuracy or absolute errors in forecasting air pollution in a traffic tunnel: the Grey model (GM), the Crank-Nicholson implicit scheme model, and the forecasting combination model (FCM). Three criteria, root mean square error (RMSE), the mean absolute error (MAE) and mean absolute percentage error (MAPE), were applied to the models and the FCM model displayed all of the characteristics of a good forecasting model. The correlation coefficient (r) for the FCM model equaled 0.94 (Upwind), 0.98 (Middle) and 0.98 (Downwind). This study indicated that FCM can be used to accurately forecast CO pollution in the Kaohsiung Cross Harbor Tunnel.


air quality Crank-Nicholson implicit scheme model (CNM) forecasting combination models (FCM) grey model (GM) traffic tunnel 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bunn, D. W.: 1989, ‘Forecasting with more than one model’, J. Forecasting 8, 161–166.Google Scholar
  2. Bunn, D. W.: 1996, ‘Non-traditional methods of forecasting’, Eur. J. Operat. Research 92, 528–536.Google Scholar
  3. Buckland, A. T. and Middleton, D. R.: 1999, ‘Nomograms for calculating pollution within street canyons’, Atmos. Environ. 33, 1017–1036.CrossRefGoogle Scholar
  4. Chen, J. Y. and Lin, Y. H.: 1996, ‘Design of fuzzy sliding mode controller with grey predictor’, J. Grey System 8, 147–164.Google Scholar
  5. Chatfield, C.: 1996, ‘Model uncertainty and forecast accuracy’, J. Forecasting 15, 495–508.Google Scholar
  6. Chiang, H. K. and Tseng, C. H.: 2004, ‘Design and implementation of a grey sliding mode controller for synchronous reluctance motor drive’, Control Eng. Practice 12, 155–163.CrossRefGoogle Scholar
  7. Deng, J. L.: 1986, ‘Grey Forecasting and Decision, Huazhong University of Science and Technology Press’, Wuhan, 97–134.Google Scholar
  8. Deng, J. L.: 1989, ‘Introduction to Grey system theory’, J. Grey System 1, 1–24.Google Scholar
  9. Donaldson, R. G. and Kamstra, M.: 1996, ‘Forecast combining with neural networks’, J. Forecasting 15, 49–61.Google Scholar
  10. Hsu, C. I. and Wen, Y. H.: 2000, ‘Application of Grey theory and multi-objective programming towards airline network design’, Eur. J. Operat. Research 127, 44–68.Google Scholar
  11. Lin, M. D. and Lin, Y. C.: 2002, ‘The application of GIS to air quality analysis in Taichung City, Taiwan, ROC’, Environ. Model. Software 17, 11–19.Google Scholar
  12. Manning, A. J., Nicholson, K. J., Middleton, D. R. and Rafferty, S. C.: 2000, ‘Field study of wind and traffic to test a street canyon pollution model’, Environ. Monit. Assess. 60, 283–313.CrossRefGoogle Scholar
  13. Makridakis, S., Andersen, A., Carbone, R., Fildes, R., Hibon, M., Lewandowski, R., Newton, J., Parzen, E. and Winkler, R.: 1982, ‘The accuracy of extrapolation (time series) methods: Results of a forecasting competition’, J. Forecasting 1, 111–153.Google Scholar
  14. Oettl, D., Sturm, P. J., Bacher, M., Pretterhofer, G. and Almbauer, R. A.: 2002, ‘A simple model for the dispersion of pollutants from a road tunnel portal’, Atmos. Environ. 36, 2943–2953.CrossRefGoogle Scholar
  15. Sharma, P. and Khare, M.: 2001, ‘Modeling of vehicular exhausts–a review’, Transport. Research D6, 179–198.Google Scholar
  16. Tseng, F. M., Yu, H. C. and Tzeng, G. H.: 2001, ‘Applied hybrid Grey model to forecast seasonal time series’, Technol. Forecasting Social Change 67, 291–302.Google Scholar
  17. Wang, M. H. and Hung, C. P.: 2003, ‘Novel grey model for the prediction of trend of dissolved gases in oil-filled power apparatus’, Electric Power Systems Research 67, 53–58.Google Scholar
  18. Yokum, J. T. and Armstrong, J. S.: 1995, ‘Beyond Accuracy: Comparison of criteria used to select forecasting methods’, Inter. J. Forecasting 11, 591–597.Google Scholar
  19. Yuan, C. S. and Hung, C. H.: 1998, ‘On-Site Investigation of Toxic Air Pollutants in the Subway Tunnels in Kaohsiung City. (Taiwan) Environ’, Protection Bureau, Kaohsiung.Google Scholar
  20. Zhang, G.: 2003, ‘Time series forecasting using a hybrid ARIMA and neural network model’, Neurocomputing 50, 159–175.Google Scholar

Copyright information

© Springer Science + Business Media, Inc. 2006

Authors and Affiliations

  • Cheng-Chung Lee
    • 1
    • 3
  • Terng-Jou Wan
    • 2
  • Chao-Yin Kuo
    • 2
  • Chung-Yi Chung
    • 3
  1. 1.Graduate School of Engineering Science and TechnologyNational Yunlin University of Science and TechnologyTaiwan
  2. 2.Institute of Safety Health and Environmental EngineeringNational Yunlin University of Science and TechnologyTaiwan
  3. 3.Department of Environmental Engineering and ScienceTajen Institute of TechnologyTaiwan

Personalised recommendations