Maritime Anomaly Detection in Baltic Sea AIS Trajectories via Ensemble Methods and Probabilistic Roadmaps

Abstract

Effective maritime anomaly detection is essential for ensuring navigational safety and safeguarding critical underwater infrastructure. In this paper, a supervised anomaly detection framework is proposed, which is tailored to the Baltic Sea, a region characterized by dense maritime traffic and recurrent submarine cable disruptions. The proposed approach uses Probabilistic Roadmaps (PRMs) to model feasible maritime routes, providing a spatial and contextual structure for feature extraction from Automatic Identification System (AIS) data. To address the lack of labeled anomalies, synthetic anomalous trajectories are generated using sinusoidal deviations, Markov-chain-driven movements, autoencoder-based transformations, and context-aware speed perturbations near submarine cables. Trajectory projections onto the PRM graph enable the extraction of geometric, behavioral, and context-aware features capturing navigational deviations and interactions with coastal and cable-rich regions. Feature selection is guided by Random Forest Importance (RFI) scores, with Recursive Feature Elimination (RFE) used to retain the most informative attributes. Optimized tree-based and ensemble classifiers support anomaly discrimination across cross-validation experiments on a balanced dataset of 858 real general cargo vessel trajectories and an equal number of synthetically generated anomalous ones. Tree-based models achieve validation ROC AUC scores above 0.81, with Random Forest reaching the highest validation accuracy of 73.2%. The soft-voting ensemble attains the highest validation precision (76.0%), favoring false-positive minimization in operationally sensitive settings. The framework is further evaluated on real-world trajectories associated with documented cable-severing incidents, illustrating its potential operational applicability while highlighting the need for broader external validation.