Models for predicting aircraft motion are an important component of modern\naeronautical systems. These models help aircraft plan collision avoidance\nmaneuvers and help conduct offline performance and safety analyses. In this\narticle, we develop a method for learning a probabilistic generative model of\naircraft motion in terminal airspace, the controlled airspace surrounding a\ngiven airport. The method fits the model based on a historical dataset of\nradar-based position measurements of aircraft landings and t…