Neural network model for predicting peak photochemical pollutant levels
Melas D., Kioutsioukis I. and Ziomas I.
[abstract] In this paper, an attempt is made for the 24-hr prediction of photochemical pollutant levels using a neural network model. For this purpose, a model is developed that relates peak pollutant concentrations to meteorological and emis-sion variables and indexes. The analysis is based on mea-surements of O 3 and NO 2 from the city of Athens. The meteorological variables are selected to cover atmospheric processes that determine the fate of the airborne pollut-ants while special care is taken to ensure the availability of the required input data from routine observations or fore-casts. The comparison between model predictions and ac-tual observations shows a good agreement. In addition, a series of sensitivity tests is performed in order to evaluate the sensitivity of the model to the uncertainty in meteoro-logical variables. Model forecasts are generally rather in-sensitive to small perturbations in most of the input meteorological data, while they are relatively more sensi-tive in changes in wind speed and direction.
[keywords] Gas fuel analysis; Mathematical models; Meteorology; Neural networks; Nitrogen oxides; Ozone; Perturbation techniques; Photochemical reactions, Airborne pollutants; Photochemical pollutant levels, Air pollution, accuracy; air pollutant; air pollution; air
J. Air Waste Management Assoc. 50 (4), 495-501, 2000
Ελληνική έκδοση
back to publications list
