Two Neural Network Methods in Estimation of Air Pollution Time Series

  • Hikmet Kerem Cigizoglu
  • Kadir Alp
  • Müge Kömürcü
Part of the Nato Science Series: IV: Earth and Environmental Science book series (NAIV, volume 62)


The measurement of air pollution parameters is a costly process. Due to several reasons, the devices may not take measurements for certain days. In such cases robust estimation methods are quite necessary in order to fill the gaps in the time series. Artificial neural networks have been employed successfully for this purpose for hydrometeorological time series, as reported in literature. In this study, modelling of the time series of air pollution parameters was investigated using two ANN methods; a radial basis function algorithm (RBF) and feed forward back propagation method (FFBP). The ANN methods were employed to estimate the PM10 values using the NO and CO values. The data were from a measurement station in Istanbul, Turkey. The results of an initial statistical analysis were considered in the determination of the input layer node number. In the estimation study, values corresponding to other air pollution parameters were included in the input layer. The results were compared to those obtained with a conventional multi-linear regression (MLR) method.


Artificial Neural Network Mean Square Error Radial Basis Function India Summer Monsoon Rainfall Neural Network Method 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abdul-Wahab, S A. and S. M. Al-Alawi; Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks, Environ. Model. Software 17 (2002) 219–228.Google Scholar
  2. Aires, F., A. Chedin, N.A. Scott and W.B. Rossow; A regularized neural net approach for retrieval of atmospheric and surface temperatures with the IASI Instrument. J. Appl. Meteorol. 41 (2002) 144–159.CrossRefGoogle Scholar
  3. ASCE Task Committee; Artificial neural networks in hydrology I, J. Hydrol. Eng. 5 (2000) 115–123.Google Scholar
  4. Bodri, L. and V. Cermak; Prediction of extreme precipitation using a neural network: application to summer flood occurrence in Moravia. Adv. Eng. Software 31 (2000) 211–221.CrossRefGoogle Scholar
  5. Broomhead, D. and D. Lowe; Multivariable functional interpolation and adaptive networks. Complex Syst. 2 (1988) 321–355.Google Scholar
  6. Cigizoglu, H. K.; Incorporation of ARMA models into flow forecasting by artificial neural networks, Environmetrics 14 (2003a) 417–427.CrossRefGoogle Scholar
  7. Cigizoglu, H. K.; Estimation, forecasting and extrapolation of flow data by artificial neural networks. Hydrol. Sci. J. 48 (2003b) 349–361.CrossRefGoogle Scholar
  8. Cigizoglu, H. K.; Estimation and forecasting of daily suspended sediment data by multi layer perceptrons. Adv. Water Resour. 27 (2004) 185–195.CrossRefGoogle Scholar
  9. Cigizoglu, H.K., K. Alp and M. Kömürcü; Estimation of air pollution parameters using artificial neural networks, in: Advances in air pollution modelling for environmental security. NATO Advanced Research Workshop, 8–12 May 2004, Borovetz. Kluwer Academic Publisher, Dordrecht (2004).Google Scholar
  10. Cigizoglu, H.K. and O. Kisi; Flow prediction by two back propagation techniques using k-fold partitioning of neural network training data. Nordic Hydrol. 36 (2005) (in press).Google Scholar
  11. Duncan, K. and W.C. Potter; Ozone modeling using neural networks, J. Appl. Meteorol. 39 (2000) 291–296.Google Scholar
  12. Gardner, M. and S. Dorling; Artificial neural network – derived trends in daily maximum surface ozone concentrations, J. Air Waste Manage. Assoc. 51 (2001) 1202–1210.Google Scholar
  13. Hagan, M.T. and M.B. Menhaj; Training feedforward techniques with the Marquardt algorithm, IEEE Trans. Neural Networks 5 (1994) 989–993.CrossRefGoogle Scholar
  14. Kuligowski, R.J. and A.P. Barros; Combined IR-microwave satellite retrieval of temperature and dewpoint profiles using artificial neural networks, J. Appl. Meteorol. 40 (2001) 205–2067.Google Scholar
  15. Luk, K.C., J.E. Ball and A. Sharma; A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting, J. Hydrol. 227 (2000) 56–65.CrossRefGoogle Scholar
  16. Maier, H.R. and G.C. Dandy; Neural network for the prediction and forecasting of water resources variables: a review of modeling issues and applications, Environ. Model. Software 15 (2000) 101–124.Google Scholar
  17. McKendry, I.G.; Evaluation of artificial neural networks for fine paniculate pollution (PM10 and PM2.5) forecasting. J. Air Waste Manage. Assoc. 52 (2002) 1096–1101.Google Scholar
  18. Narasimhan, R., J. Keller, G. Subramaniam, E. Raasch, B. Croley, K. Duncan and W.C. Potter; Ozone modeling using neural networks, J. Appl. Meteorol., 39 (2000) 291–296.CrossRefGoogle Scholar
  19. Sahai, A.K., M.K. Soman and V. Satyan; All India summer monsoon rainfall prediction using an artificial neural network, Clim. Dyn. 16 (2000) 291–302.CrossRefGoogle Scholar
  20. Silverman, D. and J.A. Dracup; Artificial neural networks and long-range precipitation prediction in California, J. Appl. Meteorol. 39 (2000) 57–66.Google Scholar
  21. Seinfeld, J.H. and S. N. Pandis; Atmospheric chemistry and physics, John Wiley & Sons Inc., New York 1998,Google Scholar
  22. U.S. EPA (Environmental Protection Agency); Latest findings on national air quality: 2002 status and trends,, accessed on 15th February 2004.Google Scholar
  23. Wayne, R.P.; Chemistry of atmospheres, Oxford University Press, New York 2000.Google Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  • Hikmet Kerem Cigizoglu
    • 1
  • Kadir Alp
    • 2
  • Müge Kömürcü
    • 2
  1. 1.Division of HydraulicsTurkey
  2. 2.Environmental Engineering DepartmentCivil Engineering Faculty, Istanbul Technical UniversityIstanbulTurkey

Personalised recommendations