The increase of carbon monoxide in the ambient air due to the emissions from point sources without control was estimated using three -dimensional numerical models. The target area was Ulsan where one of the largest industrial complexes was located. As a typical example using numerical models for air quality impact analysis of criteria pollutants that will determine whether the air quality standards would be exceeded or not, the following approaches were suggested. They include: (1) investigation of pre-existing atmospheric conditions, (2) identification of major factors causing high concentrations, (3) selection of episode days. (4) preparation of three-dimensional meteorological data, (5) confirmation of agreement between measured and predicted concentrations in the emission conditions of episode days, and (6) estimation of the impact due to changes of the emission conditions. In the present work, daily meteorological conditions for the specific period were classified into four clusters of distinctive features, and the episode days were selected individually from each cluster. Emphasis was placed on the selection of episodes representing meteorological conditions conducive to high concentrations especially for point sources that were sensitive to the wind direction variations.