The purpose of this study is to predict the hourly concentration of NO₂ in the ambient air. An artificial neural network (ANN) is used as prediction method. The ANN with three layers is learned with past data, and the concentration of air pollutant NO₂ is predicted based on the pre-learned weights. The error back propagation method is adopted as the learning rule. The model can predict the hourly mean air pollutant NO₂ based on parameters like traffic flow, temperature, relative humidity, sunspot number wind speed, and wind direction. The model can perform well both in training and independent periods. The classical methods of short term modeling are not reliable enough. The method gives an acceptable accuracy for the limited prediction horizon.