Water, Air, & Soil Pollution: Focus

, Volume 3, Issue 5–6, pp 307–316 | Cite as

Prediction of Ground Level SO2 Concentration using Artificial Neural Networks

  • Arslan SaralEmail author
  • Ferruh Ertürk


Future (24 h later) daily ground level SO2 concentration in Istanbul was modeled and predicted using a new and powerful technique, Artificial Neural Networks (ANN) in the case of meteorological parameters as input variables. Results show that the trend of SO2 from higher values in winter to lower values in spring and summer, and again to higher values towards winter can be correctly represented by the neural networks. The model better predicted the lower SO2 values in spring and summer seasons when compared to higher values in winter season because of the pattern distribution in training data sets. Beside the amount of the database, the more the variation of the values of the parameters in their own ranges, the more the network learns the database. As a result of this study, considerably successful results were obtained when considering the complex and nonlineer structure of the atmosphere, which is the source of the database.

air pollution modeling artificial neuralnetworks multi layer perceptron 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Boznar, M., Lesjak M. and Mlakar P.: 1993, ‘A neural network based method for short term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain’, Atm. Env., Vol. 27B(2), 221–230CrossRefGoogle Scholar
  2. Boznar, M. and Mlakar, P.: 1995, ‘Neural networks - A new mathematical tool for air pollution modeling’, Air pollution III Volume 1. Air Pollution Theory and Simulation, Computational Mechanics Publications, pp. 259–266, Southampton Boston.Google Scholar
  3. Ertürk, F., Karaca, M., Tayanç, M. and Saral, A., 1995, ‘Preparation of air pollution maps of Istanbul and determination of precedence of areas for natural gas network installation’, Research Project, Municipality of Istanbul Greater City.Google Scholar
  4. Gardner, M.W. and Dorling, S. R.: 1998, ‘Artificial neural networks (the multi layer perceptron) - A review of applications in the atmospheric sciences’, Atm. Env. 32(14/15), 2627–2636.CrossRefGoogle Scholar
  5. Gardner, M. W. and Dorling, S. R.: 1999, ‘Neural network modeling and prediction of hourly NOx and NO2 concentrations in urban air in London’, Atm. Env. 33, 709–719.CrossRefGoogle Scholar
  6. Gardner, M. W. and Dorling, S. R.: 2000, ‘Statistical surface ozone models: an improved methodology to account for non-linear behavior’, Atm. Env. 34, 21–34.CrossRefGoogle Scholar
  7. Goncaloğlu, B. İ.: 2001, ‘Istanbul'daki Sanayi Tesislerinden Yanma Sonucu Atmosfere Atilan Hava Kirleticilerinin Emisyon Envanterinin Çikarilmasi (Preparation of Emission Inventory for the Major Pollutants emitted from from Industrial Sources by Combustion to the Atmosphere in Istanbul)’, PhD Thesis, Yildiz Technical University, Istanbul.Google Scholar
  8. Mlakar, P. and Boznar, M.: 1994, ‘Short term air pollution prediction on the basis of artificial neural networks’, Air Pollution II Volume 1: Computer Simulation, Computational Mechanics Publications, pp. 545–552, Southampton Boston.Google Scholar
  9. Mlakar, P. and Boznar, M.: 1996, ‘Analysis of winds and SO2 concentrations in complex terrain’, Air Pollution IV: Monitoring, Simulation and Control, Computational Mechanics Publications, pp. 455–464.Google Scholar
  10. Mlakar, P. and Boznar, M.: 1997, ‘Perceptron neural network - Based model predicts air pollution’, Proceedings on Intelligent Information Systems, IIS'97, IEEE Computer Society, 0–8186–8218–3, pp. 345–349.Google Scholar
  11. Perautonis, S. J., Vassilas, N. and Amanatidis, G. T. et al.: 1994, ‘Neural network techniques for SO2 episode prediction’, Air Pollution Modeling and Its Application X, Plenum Press, pp. 305–313, New York.Google Scholar
  12. Reich, S. L., Gomez, D. R. and Dawidowski, L. E.: 1999, ‘Artificial neural networks for the identification of unknown air pollution sources’, Atm. Env. 33, 3045–3052.CrossRefGoogle Scholar
  13. Rumelhart, D. E. and McClelland, J. L.: 1986, Parallel Distributed Processing 1,2, MIT Press, Cambridge, MA.Google Scholar
  14. Saral, A.: 1995, ‘Istanbul'un Hava Kirliligi Haritalarinin Çikarilmasi’ (Preparation of Air pollution Maps of Ístanbul), MS Thesis, Yildiz Technical University, Istanbul.Google Scholar
  15. Saral, A.: 2000, ‘Air pollution modelling and prediction by artificial neural networks’, PhD Thesis, Yildiz Technical University.Google Scholar

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  1. 1.Dept. of Environmental EngineeringYıldız Technical UniversityBesiktas, IstanbulTurkey

Personalised recommendations