A Neural Network Approach to Study O3 and PM10 Concentration in Environmental Pollution

  • Giuseppe Acciani
  • Ernesto Chiarantoni
  • Girolamo Fornarelli
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4132)


In this paper two artificial neural networks are trained to determine Ozone and PM10 concentrations trying to model the environmental system. Then a method to partition the connection weights is used to calculate a relative importance index which returns the relative contribution of each chemical and meteorological input to the concentrations of Ozone and PM10. Moreover, an investigation of the variances of the input in the observation time contribute to understand which input mainly influence the output. Therefore a neural network trained only by the variables with higher values of relative importance index and low variability is used to improve the accuracy of the proposed model. The experimental results show that this approach could help to understand the environmental system.


Neural Network Hide Layer Ozone Concentration Meteorological Variable Connection Weight 
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. 1.
    Corani, G.: Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning. Ecological Modelling 185, 513–529 (2005)CrossRefGoogle Scholar
  2. 2.
    Acciani, G., Chiarantoni, E., Fornarelli, G., Vergura, S.: A Feature Extraction Unsupervised Neural Network for Environmental Data Set. Neural Networks 16, 427–436 (2003)CrossRefGoogle Scholar
  3. 3.
    Mintz, R., Young, B.R., Svrcek, W.Y.: Fuzzy logic modeling of surface ozone concentrations. Computers and Chemical Engineering 29, 2049–2059 (2005)CrossRefGoogle Scholar
  4. 4.
    Hooyberghsa, J., Mensinka, C., Dumontb, G., Fierensb, F., Brasseurc, O.: A neural network forecast for dailyaverage PM10 concentrations in Belgium. Atmospheric Environment 39, 3279–3289 (2005)CrossRefGoogle Scholar
  5. 5.
    Abdollahian, M., Foroughi, R.: Optimal statistical model for forecasting ozone. In: International Conference on Information Technology: Coding and Computing, April 4-6, vol. 1, pp. 169–173 (2005)Google Scholar
  6. 6.
    Jeong-Sook, H., Dong-Sool, K.: A new method of ozone forecasting using fuzzy expert and neural network systems. Science of the Total Environment 325, 221–237 (2004)CrossRefGoogle Scholar
  7. 7.
    Elkamel, A., Abdul-Wahab, S., Bouhamra, W., Alper, E.: Measurement and prediction of ozone levels around a heavily industralized area: a neural network approach. Advances in environmental research 5, 47–59 (2001)CrossRefGoogle Scholar
  8. 8.
    Muir, D.: PM10 Particulates in Relation to Other Atmospheric Pollutants, vol. 52, pp. 29–42. Kluwer Academic Publishers, Dordrecht (1998)Google Scholar
  9. 9.
    Barrero, M.A., Grimalt, J.O., Cantòn, L.: Prediction of daily ozone concentration maxima in the urban atmosphere. Chemometrics and Intelligent Laboratory Systems 80, 67–76 (2006)CrossRefGoogle Scholar
  10. 10.
    Brunekreef, B., Holgate, S.T.: Air pollution and Health. The Lancet 360, 1233–1242 (2002)CrossRefGoogle Scholar
  11. 11.
    Garson, G.D.: Interpreting Neural Network Connection Weights. AI Expert, 47–51 (1991)Google Scholar
  12. 12.
    Borri, D., Concilio, G., Conte, E.: A KBDSS for traffic air pollution control in urban environment. In: CUPUM Computers in Urban Planning and Urban Management Conference, Hawaii, pp. 10–14 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Giuseppe Acciani
    • 1
  • Ernesto Chiarantoni
    • 1
  • Girolamo Fornarelli
    • 1
  1. 1.Politecnico di Bari, Dipartimento di Elettronica ed ElettrotecnicaBariItaly

Personalised recommendations