Identification of important traffic safety parameters in road tunnels

Tunnels are one of the most important accident-prone zones due to their physical and functional difference from open parts of the road whereas crash-prediction models for road tunnels have rarely been investigated. The main purpose of this study is to identify important parameters that affect the traffic safety in tunnels. In this paper, linear regression, Poisson regression, Negative binominal regression and Zero inflated regressions models are applied in order to obtain crash prediction models for property damage, serious injury and fatal accidents. The results show that the best model for property damage accidents is linear regression output. However, for fatal and injuries accidents, zero inflated regression’s results are more dependable. This paper’s suggested method appears to be useful for many applications such as the estimation of accident reductions due to improvement in existing tunnels and/or to modifications of traffic control systems, as well as for the prediction of accidents when different tunnel design options are compared. According to the final crash prediction models the most important safety characteristics of tunnels are: AADT per lane, tunnel length, heavy vehicles ratio, and number of lanes in tunnel