Measurement and prediction of ozone levels around a heavily industrializedarea: a neural network approach

This paper presents an artificial neural network model that is able to pred ict stone concentrations as a function of meteorological conditions and pre cursor concentrations. The network was trained using data collected during a period of 60 days near an industrial area in Kuwait. A mobile monitoring station was used for data collection. The data were collected at the same s ite as the ozone measurements. The data fed to the neural network were divi ded into two sets: a training set and a testing set. Various architectures were tried during the training process. A network of one hidden layer of 25 neurons was found to give good predictions for both the training and testi ng data set. In addition, the predictions of the network were compared to m easurements taken during other times of the year. The inputs to the neural network were meteorological conditions (wind speed and direction, relative humidity, temperature, and solar intensity) and the concentration of primar y pollutants (methane, carbon monoxide, carbon dioxide, nitrogen oxide, nit rogen dioxide, sulfur dioxide, non-methane hydrocarbons, and dust). A backp ropagation algorithm with momentum was used to prepare the neural network. A partitioning method of the connection weights of the network was used to study the relative % contribution of each of the input variables. It was fo und that the precursors carbon monoxide, carbon dioxide, nitrogen oxide, ni trogen dioxide, and sulfur dioxide had the most effect on the predicted ozo ne concentration. In addition, temperature played an important role. The pe rformance of the neural network model was compared against linear and non-l inear regression models that were prepared based on the present collected d ata. It was found that the neural network model consistently gives superior predictions. Based on the results of this study, artificial neural network modeling appears to be a promising technique for the prediction of polluta nt concentrations. (C) 2001 Elsevier Science Ltd. All rights reserved.