Clustering Days and Hours with Similar Airport Traffic and Weather Conditions

摘要

On any given day, constraints in the National Airspace System (for instance, weather) necessitate the implementation of traffic flow management initiatives, such as ground delay programs. The goal of this study is to take a preliminary step toward informing future decision making by applying data-mining techniques to identify similar days in the National Airspace System in terms of the cause and location of historically implemented ground delay programs. In the first part of this study, a modified K-means clustering algorithm was applied to all days from 2010 through 2012, resulting in the identification of 45 national-level daily clusters that represent unique combinations of historically implemented ground delay programs. The second part of this study focused on verifying the stated causes of the historical ground delay programs. Findings from this initial study indicated that it is possible to identify similar days under which the National Airspace System operates, and clustering techniques appear to be promising methods for identifying the major causes of ground delay programs.