A Neural Network Approach to Study O3 and PM10 Concentration in Environmental Pollution
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.
KeywordsNeural Network Hide Layer Ozone Concentration Meteorological Variable Connection Weight
Unable to display preview. Download preview PDF.
- 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
- 8.Muir, D.: PM10 Particulates in Relation to Other Atmospheric Pollutants, vol. 52, pp. 29–42. Kluwer Academic Publishers, Dordrecht (1998)Google Scholar
- 11.Garson, G.D.: Interpreting Neural Network Connection Weights. AI Expert, 47–51 (1991)Google Scholar
- 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