A study on air pollution in the city of Reggio Calabria, Italy, took place for a period of three months in 1997, centred on road traffic related pollutants by monitoring the concentration of carbon monoxide on a main street in the city centre. The comparison of the present data with the results of an air pollution monitoring campaign which the authors led in 1993 and part of 1994, aims to determine an experimental model for the forecasting of CO concentrations. The concentration of carbon monoxide was chosen as the most representative air pollutant because of its direct dependence on vehicular emissions, and also the lack of industrial areas in Reggio Calabria results in CO emissions being due almost exclusively to road traffic. The chemical data measured is carbon monoxide, and the meteorological data is wind speed and direction, temperature, cloud cover and atmospheric pressure. Measurements of traffic flows were also taken. The peculiarity of the setting, high traffic flows on an urban road with a low average speed were the premises for particularly high concentration values, but the physical characteristics of the location, and the influence of meteorological factors lowered effects below expected values. On the basis of the results of air pollution monitoring in different times of the year in the same location, a statistical model was obtained, for the purpose of determining concentrations in function of traffic and meteorological data. Application of such a model on a study period gave reliable results. Even if such a model is not reliable in determining concentrations of carbon monoxide in specific locations with different features, it is adaptable to the main traffic arteries of the city, giving a valid indication of the presence of concentrations which exceed the limits set by the current legislation.