This paper describes a general methodology for calibration of air pollutants dispersion models. Numerical simulation of this phenomenon is a complex process due to it depends on many factors. Main contribution of this paper is to consider in a unique calibration methodology of uncertainty and sensitivity analysis. Furthermore, the methodology is applied successfully in the calibration process gaussian dispersion model ISCST3 applied in a densely populated area, the Higher Polytechnic Institute José Antonio Echeverría (CUJAE) in Havana.