Effective and Efficient Representation Learning for Flight Trajectories

TL;DR

This work tackles the need for a unified representation of flight trajectories that can support multiple downstream tasks. It introduces Flight2Vec, a two-pronged approach combining behavior-adaptive patching and motion trend learning within a patch-based Transformer framework, optimized by mask-based self-supervision and a moving-direction loss to capture 3D spatial continuity. The proposed method addresses the challenges of unbalanced behavior density and 3D motion in aviation data, demonstrating significant improvements in trajectory prediction, anomaly detection, and flight recognition on real datasets while maintaining favorable efficiency. The results suggest Flight2Vec as a practical, scalable tool for flight trajectory analysis with broad applicability in air traffic management and safety monitoring.

Abstract

Flight trajectory data plays a vital role in the traffic management community, especially for downstream tasks such as trajectory prediction, flight recognition, and anomaly detection. Existing works often utilize handcrafted features and design models for different tasks individually, which heavily rely on domain expertise and are hard to extend. We argue that different flight analysis tasks share the same useful features of the trajectory. Jointly learning a unified representation for flight trajectories could be beneficial for improving the performance of various tasks. However, flight trajectory representation learning (TRL) faces two primary challenges, \ie unbalanced behavior density and 3D spatial continuity, which disable recent general TRL methods. In this paper, we propose Flight2Vec , a flight-specific representation learning method to address these challenges. Specifically, a behavior-adaptive patching mechanism is used to inspire the learned representation to pay more attention to behavior-dense segments. Moreover, we introduce a motion trend learning technique that guides the model to memorize not only the precise locations, but also the motion trend to generate better representations. Extensive experimental results demonstrate that Flight2Vec significantly improves performance in downstream tasks such as flight trajectory prediction, flight recognition, and anomaly detection.

Figures (5)

• Figure 1: The motivation of Flight2Vec
• Figure 2: Overview of Flight2Vec
• Figure 3: Behavior-Based Patching
• Figure 4: Illustration of Motion Trend Learning
• Figure 5: MDE scores with varying model parameters.