The primary air pollutants in the Beijing urban area are fine particulate matter (PM 10 ), sulfur dioxide (SO 2 ), and nitrogen oxides (NO x ). Using suitable emission factors for point, area, and line sources from 20 categories of industrial, commercial, domestic and traffic, total yearly mean emissions were estimated at 103.3 kton of PM 10 , 209.9 kton of SO 2 , and 225.4 kton of NO x in 1999. To abate this elevated air pollution, three air quality management schemes are adopted. After the implementation, the annual mean ground-level concentrations of air pollutants are predicted by an industrial source complex short term (ISCST3) dispersion model and compared by the geographic information system (GIS). The ISCST3 dispersion model is used by inputting emission inventory and meteorological data with 1 h temporal and 1 km  1 km spatial resolution. The model validity is verified by its agreement with monitoring data from Beijing's Environmental Protection Bureau. Results indicate that the levels of PM 10 , SO 2 , and NO x in Beijing are improved gradually because of the adoption of these three control schemes.