Real-Time Vessel Anomaly Detection Based on Transformer Trajectory Prediction Using AIS Data

Abstract

Automatic Identification System data provide continuous vessel movement information and have become an important data source for maritime traffic monitoring. However, abnormal vessel behavior is difficult to detect in real time because AIS trajectories are noisy, irregularly sampled, and strongly affected by navigation environments. To address this problem, this paper proposes a real-time vessel anomaly detection method based on Transformer trajectory prediction. Historical normal trajectories are first preprocessed and represented through a discrete four-hot encoding scheme. A Transformer-based sequence model is then trained to learn normal vessel movement patterns and predict the vessel position at the next time step. During online detection, the predicted position is compared with the observed AIS position, and a position anomaly is identified when the prediction error exceeds a region-specific threshold. Experiments are conducted on AIS trajectories collected from three representative waters, including Chengshantou, the Yangtze River Estuary, and the Zhoushan Islands. The experimental results show that the proposed method achieves competitive trajectory prediction accuracy and improves real-time anomaly detection performance compared with several baseline methods. The results indicate that Transformer-based trajectory prediction can provide effective support for intelligent maritime supervision and vessel traffic safety management.