Pollution prevention and control is one of the three key issues in China recently. Telecom operators have the data of millions of users, including identity attributes, mobile trajectories, and service behavior characteristics etc. On the premise of guaranteeing user data security, pollution prevention and control work can be extended from the source control, transmission characteristics and other aspects to the impact on the population. Thus, it can realize the comprehensive assessment of pollution prevention and control. This paper focuses on the field of air pollution prevention and control. We propose a refined pollution prevention and control method based on telecom operator data. This method can predict the users' distribution. Furthermore, it can analyze and predict the impacted users of air pollution, and finally to assist the Chinese "Blue Sky Plan".