Title: NN-AirPol: a neural-networks-based method for air pollution evaluation and control

Authors: Ferhat Karaca, Alexander Nikov, Omar Alagha

Addresses: Department of Environmental Engineering, Fatih University, 34900 Buyukcekmece, Istanbul, Turkey. ' Department of Industrial Engineering, Fatih University, 34900 Buyukcekmece, Istanbul, Turkey. ' Department of Environmental Engineering, Fatih University, 34900 Buyukcekmece, Istanbul, Turkey

Abstract: A method for air pollution evaluation and control, based on one of the most popular neural networks – the backpropagation algorithm, is proposed. After the backpropagation training, the neural network, based on weather forecasting data, determines the future concentration of critical air pollution indicators. Depending on these concentrations, relevant episode warnings and actions are activated. A case study is carried out to illustrate and validate the method proposed, based on Istanbul air pollution data. Sulphur dioxide and inhalable particulate matter are selected as air pollution indicators (neural network outputs). Relevant episode measures are proposed. Among ten backpropagation algorithms, the BFGS algorithm (Quasi-Newton algorithms) is adopted since it showed the lowest training error. A comparison of NN-AirPol method against regression and perceptron models showed significantly better performance.

Keywords: air pollution; modelling; backpropagation algorithms; optimisation; environmental pollution; pollution evaluation; pollution control; neural networks; weather forecasting data; Turkey; training errors.

DOI: 10.1504/IJEP.2006.011214

International Journal of Environment and Pollution, 2006 Vol.28 No.3/4, pp.310 - 325

Published online: 06 Nov 2006 *

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