Trajectory analysis is one of the canonical applications of data science to aviation. In this talk, I will summarize some standard methods and recent research related to the analysis of flight trajectories. First, trajectory clustering methods will be overviewed and applied to identify common routes between selected US domestic city pairs. We will discuss feature engineering for trajectories in order to investigate how weather, winds, and traffic management initiatives affect the assignment of individual flights to different alternative routes. A generative model, which predicts the future evolution of a specific flight trajectory based on its flight plan, weather conditions, and trajectory history, will then be presented. Finally, we will consider the identification of “anomalous” trajectories with specific focus on the analysis and prediction of “go-arounds” of flights attempting to land at JFK airport.
Speaker: Mark Hansen, UC Berkeley
Other Dates For This Event:
Contact:Website: Click to Visit
Save this Event:iCalendar
Windows Live Calendar