Trajectory Clustering within the Terminal Airspace Utilizing a Weighted Distance Function

Abstract

To support efforts to modernize aviation systems to be safer and more efficient, high-precision trajectory prediction and robust anomaly detection methods are required. The terminal airspace is identified as the most critical airspace for individual flight-level and system-level safety and efficiency. To support successful trajectory prediction and anomaly detection methods within the terminal airspace, accurate identification of air traffic flows is paramount. Typically, air traffic flows are identified utilizing clustering algorithms, where performance relies on the definition of an appropriate distance function. The convergent/divergent nature of flows within the terminal airspace makes the definition of an appropriate distance function challenging. Utilization of the Euclidean distance is standard in aviation literature due to little computational expense and ability to cluster entire trajectories or trajectory segments at once. However, a primary limitation in the utilization of the Euclidean distance is the uneven distribution of distances as aircraft arrive at or depart from the airport, which may result in skewed classification and inadequate identification of air traffic flows. Therefore, a weighted Euclidean distance function is proposed to improve trajectory clustering within the terminal airspace. In this work, various weighting schemes are evaluated, applying the HDBSCAN algorithm to cluster the trajectories. This work demonstrates the promise of utilizing a weighted Euclidean distance function to improve the identification of terminal airspace air traffic flows. In particular, for the selected terminal airspace, if trajectory points closer to the border of the terminal airspace, but not necessarily at the border, are weighted highest, then a more accurate clustering is computed.

Keywords

• trajectory clustering
• HDBSCAN
• machine learning
• ADS-B
• air traffic management