In this study we investigated the air pollutants dispersion around depressed road using commercial FLUENT CFD code. In order to find optimal turbulence model which simulates air pollution dispersion around. depressed road, we used the realizable k-ε model, the RNG k-ε model, and the Shear-Stress Transport k-⍵turbulence model in FLUENT CFD code. The results were compared with the wind tunnel experiments. Realizable k-ε turbulence model provided the best prediction for the surface concentrations and concentration profiles of selected downwind positions of the depressed road. It was found that a noise barrier, which positioned around the depressed road, decrease the horizontal impact distance lower 0.46~0.81 times and change the vertical air pollution impact distance larger 0.95~1.47 times than those of no barrier case. It was also found that two or three noise barriers increase 1.33-1.42 times the vertical air pollution impact distance. It contributes the decrease of horizontal air pollution impact distance 0.44~0.60 times compare with no barrier case.