Neural network model for maximum ozone concentration prediction

  • Gonzalo Acuña
  • Héctor Jorquera
  • Ricardo Pérez
Oral Presentations: Applications Practical Applications
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1112)


A neural network dynamic model was used for predicting maximum ozone (O3) concentration at Santiago de Chile. Learning and test data were collected during summer and springtime periods of 1990, 1992 and 1993. A neural network having O3 t, Tt+1 (maximum air temperature) and Tt as inputs for predicting O3 t+1 was chosen because of its low test error. This neural network model greatly reduces the error coming from a pure persistence model when applied to the generalization set of data (1994). Long-term predictions results confirm the good concordance obtained between the observed and forecasted values thus showing the adequacy of neural networks to model the dynamics of this complex environmental phenomena.


Neural networks ozone forecasting dynamic modeling predictive model 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. R. Atkinson, A.C. Lloyd and L. Winges (1982), An updated chemical mechanism for hydrocarbon/NOx/SO2 photooxidants suitable for inclusion in atmospheric simulation models, Atmos. Environ., 16, 1341–1355.Google Scholar
  2. C. M. Bishop (1994), Neural networks and their applications, Rev. Sci. Instrum, 54(6), June 1994.Google Scholar
  3. E. Latrille, G. Corrieu and J. Thibault (1994), Neural network models for final process time determination in fermented milk production, Computers chem. Engng. 18, 1171–1181.Google Scholar
  4. M. Lippmann (1989), Health effects of ozone: To critical review, J. Air and Waste Manage. Assoc., 39, 672.Google Scholar
  5. G.M. McCollister and K.R. Wilson (1975), Linear Stochastic Models for Forecasting Daily Maxima and Hourly Concentrations of Air Pollutants, Atmos. Environ., 9, 417–423.Google Scholar
  6. O. Nerrand, P. Roussel-Ragot, L. Personnaz and G. Dreyfus (1993), Neural networks and non-linear adaptive filtering: unifying concepts and new algorithms. Neural Comput. 5, 165–199.Google Scholar
  7. S.M. Robeson and D.G. Steyn (1990), Evaluation and Comparison of Statistical Forecast Models or Daily Maximum Ozone Concentrations, Atmos. Environ. 24B, 303–312.Google Scholar
  8. J. Sjöberg, Q. Zhang, L. Ljung, A. Benveniste, B. Delyon, P. Glorennec, H. Hjalmarsson and A. Juditsky (1995), Nonlinear Black-box Modeling in System Identification: a Unified Overview, Automatica, 31, 1691–1724.Google Scholar
  9. H. Su, T. McAvoy and P. Werbos (1992), Long-Term Predictions of Chemical Processes Using Recurrent Neural Networks: A Parallel Training Approach, Ind. Eng. Chem. Res., 31, 1338–1352.Google Scholar
  10. B. Tilton (1989), Health effects of tropospheric ozone, Environ. Sci. Technol., 23, 257.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Gonzalo Acuña
    • 1
  • Héctor Jorquera
    • 2
  • Ricardo Pérez
    • 2
  1. 1.CECTAUniversidad de Santiago de ChileChile
  2. 2.Departamento de Ingeniería Química y BioprocesosPontificia Universidad Católica de ChileChile

Personalised recommendations