Aircraft Trajectory Segmentation-based Contrastive Coding: A Framework for Self-supervised Trajectory Representation

Thaweerath Phisannupawong, Joshua Julian Damanik, Han-Lim Choi

Abstract

Air traffic trajectory recognition has gained significant interest within the air traffic management community, particularly for fundamental tasks such as classification and clustering. This paper introduces Aircraft Trajectory Segmentation-based Contrastive Coding (ATSCC), a self-supervised time series representation learning framework designed to capture semantic information in air traffic trajectory data, resulting in a data representation that best explains the trajectory instances. The framework leverages the segmentable characteristic of trajectories and ensures consistency within the self-assigned segments. Intensive experiments were conducted on datasets from three different airports, totaling four datasets, to compare the performance of the learned representation in downstream classification and clustering with that of other state-of-the-art representation learning techniques. The results show that ATSCC outperforms the baseline methods by aligning the representation with maneuvering procedures. Moreover, ATSCC is adaptable to various airport configurations and applicable to incomplete trajectories. This research has expanded upon existing capabilities, achieving these improvements independently without predefined inputs such as airport configurations, maneuvering procedures, or labeled data.