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

Abstract This paper presents an artificial neural network model that is able to predict ozone concentrations as a function of meteorological conditions and precursor 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 site as the ozone measurements. The data fed to the neural network were divided 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 testing data set. In addition, the predictions of the network were compared to measurements 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 primary pollutants (methane, carbon monoxide, carbon dioxide, nitrogen oxide, nitrogen dioxide, sulfur dioxide, non-methane hydrocarbons, and dust). A backpropagation 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 found that the precursors carbon monoxide, carbon dioxide, nitrogen oxide, nitrogen dioxide, and sulfur dioxide had the most effect on the predicted ozone concentration. In addition, temperature played an important role. The performance of the neural network model was compared against linear and non-linear regression models that were prepared based on the present collected data. 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 pollutant concentrations.

[1]  H. Liljestrand.  Average rainwater pH, concepts of atmospheric acidity, and buffering in open systems , 1985 .

[2]  G Kuntasal,et al.  Trends and relationships of O3, NOx and HC in the south coast air basin of California. , 1987, JAPCA.

[3]  Hisham Ettouney,et al.  Predicting ozone levels , 1996, Environmental science and pollution research international.

[4]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

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

[6]  Mahesh A Rege,et al.  A Simple Neural Network for Estimating Emission Rates of Hydrogen Sulfide and Ammonia from Single Point Sources. , 1996, Journal of the Air & Waste Management Association.

[7]  Linear regression analyses of ozone and sulphur dioxide in ambient air , 1986 .

[8]  G. Whitten,et al.  The carbon-bond mechanism: a condensed kinetic mechanism for photochemical smog. , 1980, Environmental science & technology.

[9]  John H. Seinfeld,et al.  Comparative analysis of chemical reaction mechanisms for photochemical smog , 1985 .

[10]  J H Seinfeld,et al.  Urban Air Pollution: State of the Science , 1989, Science.

[11]  Antonello Pasini,et al.  Neural Network Modelling: Perspectives of Application for Monitoring and Forecasting Physical-Chemical Variables in the Boundary Layer , 1996 .

[12]  M. C. Dodge,et al.  A photochemical kinetics mechanism for urban and regional scale computer modeling , 1989 .

[13]  John H. Seinfeld,et al.  Comparative analysis of chemical reaction mechanisms for photochemical smog—II. Sensitivity of EKMA to chemical mechanism and input parameters , 1986 .

[14]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[15]  D. R. Baughman,et al.  Neural Networks in Bioprocessing and Chemical Engineering , 1992 .

[16]  Jose Torres-Jimenez,et al.  Short-term ozone forecasting by artificial neural networks , 1995 .

[17]  Ali Elkamel,et al.  An artificial neural network for predicting and optimizing immiscible flood performance in heterogeneous reservoirs , 1998 .

[18]  Utomo Utojo,et al.  Appendix – Connections between Neural Networks and Multivariate Statistical Methods: An Overview* , 1995 .

[19]  J. Kinosian.  Ozone-precursor relationships from EKMA diagrams. , 1982, Environmental science & technology.