Title: Short-term prediction of means of artificial neural urban NO₂ pollution by networks

Authors: C. Cappa, D. Anfossi, M.M. Grosa, P. Natale

Addresses: Istituto di Cosmogeofisica del CNR, Corso Fiume 4, 10133 Torino, Italy. ' Istituto di Cosmogeofisica del CNR, Corso Fiume 4, 10133 Torino, Italy. ' ARPA, Via San Domenico 22/13, 10123 Torino, Italy. ' ARPA, Via San Domenico 22/13, 10123 Torino, Italy

Abstract: A neural network model for the short-term prediction of concentrations of urban pollutants was developed and applied to the Turin (Northern Italy) air quality network. In particular, the study was focused on NO₂ concentrations measured at five stations; t + 3 and t + 24 hour NO₂ concentration forecasting based on hourly meteorological and concentration data gave good agreement with observed concentrations. This is particularly true for the mean concentration values and concentration distribution. The time of occurrence of peak values was correctly forecast but the amounts were generally underestimated. To reduce this underestimation, an empirical step function was applied in the t + 24 case. This allowed an accurate estimate to be obtained of the few cases in which 50% of the air quality monitoring stations exceeded the attention level (200 µg m^-3) during the following day for at least one hour.

Keywords: artificial neural networks; NO₂ concentration predictions; urban air pollution.

DOI: 10.1504/IJEP.2001.004913

International Journal of Environment and Pollution, 2001 Vol.15 No.5, pp.483 - 496

Published online: 26 Jul 2004 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article