Categorizing Flight Paths using Data Visualization and Clustering Methodologies
This work addresses the problem of efficient air traffic management for aviation authorities and analysts, but it is incremental as it applies existing clustering methods to a specific dataset with minor optimizations.
The paper tackled the problem of categorizing air traffic flight paths by developing and comparing two clustering algorithms—a spatial-based geographic distance model and a vector-based cosine similarity model—using the FAA's Traffic Flow Management System dataset and the DV8 visualization tool, with results showing that geographic distance performed better for enroute portions while cosine similarity was more effective for near-terminal operations like arrivals.
This work leverages the U.S. Federal Aviation Administration's Traffic Flow Management System dataset and DV8, a recently developed tool for highly interactive visualization of air traffic data, to develop clustering algorithms for categorizing air traffic by their varying flight paths. Two clustering methodologies, a spatial-based geographic distance model, and a vector-based cosine similarity model, are demonstrated and compared for their clustering effectiveness. Examples of their applications reveal successful, realistic clustering based on automated clustering result determination and human-in-the-loop processes, with geographic distance algorithms performing better for enroute portions of flight paths and cosine similarity algorithms performing better for near-terminal operations, such as arrival paths. A point extraction technique is applied to improve computation efficiency.