In recent decades, there has been an increasing interest in the prognosis of maximum surface ozone concentrations due to the adverse effects on human health, animal population, agricultural productivity and forestry. The present study deals with the development and application of Artificial Neural Network (ANN) models in predicting the maximum daily surface ozone concentration in several locations within the greater Athens area (GAA), 24-hours in advance. Meteorological and air pollution data during the period 2001 to 2005 were provided by the network of the Hellenic Ministry of the Environment, Energy and Climate Change. Hourly values of barometric pressure and total solar irradiance for the same period have been recorded by the National Observatory of Athens. A training data set for the ANN prognostic model was generated by employing the superposed epoch analysis.
The evaluation of the performance of the developed model, using appropriate statistical indices, clearly indicates that the risk of surface ozone values exceeding the European Union (EU) threshold for human health protection can be successfully predicted. This suggests that the proposed ANN model can be used to issue warnings for the general public and especially certain sensitive groups of the population.