One of the basic parameters which describes road traffic is Annual
Average Daily Traffic (AADT). Its accurate determination is possible
only on the basis of data from the continuous measurement of traffic.
However, such data for most road sections is unavailable, so AADT must
be determined on the basis of short periods of random measurements. This
article presents different methods of estimating AADT on the basis of
daily traffic (VOL), and includes the traditional Factor Approach,
developed Regression Models and Artificial Neural Network models. As
explanatory variables, quantitative variables (VOL and the share of
heavy vehicles) as well as qualitative variables (day of the week,
month, level of AADT, the cross-section, road class, nature of the area,
spatial linking, region of Poland and the nature of traffic patterns)
were used. Based on comparisons of the presented methods, the Factor
Approach was identified as the most useful.