Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area

In this paper, we present the results obtained using three prognostic models to forecast ozone (O"3) and nitrogen dioxide (NO"2) levels in real-time up to 8h ahead at four stations in Bilbao (Spain). Two multilayer perceptron (MLP) based models and one multiple linear regression based model were developed. The models utilised traffic variables, meteorological variables and O"3 and NO"2 hourly levels as input data, which were measured from 1993 to 1994. The performances of these three models were compared with persistence of levels and the observed values. The statistics of the Model Validation Kit determined the goodness of the fit of the developed models. The results indicated improved performance for the multilayer perceptron-based models over the multiple linear regression model. Furthermore, comparisons of the results of the multilayer perceptron-based models proved that the insertion of four additional seasonal input variables in the MLP provided the ability of obtaining more accurate predictions. The comparison of the results indicated that this model performance was more efficient in the forecasts of O"3 and NO"2 hourly levels k hours ahead (k=1, 4, 5, 6, 7, 8), but not in the forecasted values 2 and 3h ahead. Future research in this area could allow us to improve results for the above forecasts. The multilayer perceptron modelling was developed using the MATLAB software package.

[1]  Sandra L. Winkler,et al.  The impact of an 8 h ozone air quality standard on ROG and NOx controls in Southern California , 1999 .

[2]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[3]  R. Derwent,et al.  World wide web site of a master chemical mechanism (MCM) for use in tropospheric chemistry models , 1997 .

[4]  Gavin C. Cawley,et al.  Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki , 2003 .

[5]  Jorge Reyes,et al.  Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile , 2000 .

[6]  Gabriel Ibarra-Berastegi,et al.  Short-term, real-time forecasting of hourly ozone, NO2 and NO levels by means of multiple linear regression modelling , 2001 .

[7]  V. Prybutok,et al.  A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area. , 1996, Environmental pollution.

[8]  Asha B. Chelani,et al.  Prediction of sulphur dioxide concentration using artificial neural networks , 2002, Environ. Model. Softw..

[9]  Ali Elkamel,et al.  Measurement and prediction of ozone levels around a heavily industrialized area: a neural network approach , 2001 .

[10]  Michael E. Chang,et al.  Ozone Predictions in Atlanta, Georgia: Analysis of the 1999 Ozone Season , 2001, Journal of the Air & Waste Management Association.

[11]  Aldo Cipriano,et al.  Forecasting ozone daily maximum levels at santiago, chile , 1998 .

[12]  P. J. Rye.  Modelling photochemical smog in the Perth region , 1995 .

[13]  Gabriel Ibarra-Berastegi,et al.  Long-term changes of ozone and traffic in Bilbao , 2001 .

[14]  H. Mayer.  Air pollution in cities , 1999 .

[15]  D. Palazzo,et al.  Europe’s Environment: The Second Assessment, by the Environment Agency, Office for Official Publications of the European Communities, Elsevier, Oxford, United Kingdom, 1998, 293 pp. , 2000 .

[16]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[17]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[18]  Richard D. Scheffe,et al.  A review of the development and application of the urban airshed model , 1993 .

[19]  Martin T. Hagan,et al.  Neural network design , 1995 .

[20]  R. Zellner,et al.  B. Finlayson‐Pitts, J. N. Pitts, Jr.: Atmospheric Chemistry: Fundamentals and Experimental Techniques, J. Wiley and Sons, New York, Chichester, Brisbane, Toronto and Singapore 1986. 1098 Seiten, Preis: £ 57.45. , 1986 .

[21]  Ana Isabel Miranda,et al.  Impact of road traffic emissions on air quality of the Lisbon region , 2000 .

[22]  R. Simpson,et al.  Forecasting peak ozone levels , 1983 .

[23]  M. Gardner,et al.  Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London , 1999 .

[24]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[25]  Klaus-Robert Müller,et al.  Asymptotic statistical theory of overtraining and cross-validation , 1997, IEEE Trans. Neural Networks.

[26]  L. L. Schulman,et al.  Hazard Response Modeling Uncertainty (A Quantitative Method) , 1988 .

[27]  Marija Zlata Boznar,et al.  A neural network-based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain , 1993 .

[28]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[29]  B. Finlayson‐Pitts,et al.  Atmospheric chemistry : fundamentals and experimental techniques , 1986 .

[30]  Stephen Dorling,et al.  Statistical surface ozone models: an improved methodology to account for non-linear behaviour , 2000 .

[31]  K. Hsu.  Time series analysis of the interdependence among air pollutants , 1992 .