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, illustrating its potential operational applicability while highlighting the need for broader external validation.
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.
Abnormal ship behavior detection is important for maritime traffic surveillance, navigation safety, and risk prevention. However, existing methods often depend on handcrafted features or a single reconstruction or prediction signal, which limits their ability to detect both sustained trajectory abnormalities and abrupt vessel movement changes. This paper proposes a Dual-Error Fusion LSTM–Transformer framework, referred to as DEFLT, for AIS-based abnormal ship behavior detection. A motion-aware vessel representation was first constructed by combining the geographical position, speed over ground, course over ground, and their temporal variations. An LSTM autoencoder reconstructs historical trajectory windows, while a Transformer prediction module estimates subsequent vessel states. The standardized reconstruction and prediction errors are fused into a unified anomaly score to capture complementary evidence from historical trajectory inconsistency and unexpected future motion. Experiments were conducted using real-world AIS data collected during September 2019 from four representative Danish waters. The study considers four abnormal behaviors: speed anomalies, course anomalies, loitering, and route deviations. Compared with KNN, LOF, Isolation Forest, Random Forest, the LSTM-AE, and the Transformer, DEFLT achieves F1-scores of 0.96, 0.97, 0.88, and 0.93 across the four study areas. For type-specific detection, the Macro-F1 values range from 0.61 to 0.86, while Macro-Recall remains between 0.88 and 0.96. Friedman and post hoc Wilcoxon signed-rank tests further demonstrate that DEFLT provides a significant and consistent improvement over all baseline methods. These results verify the effectiveness of dual-error fusion for detecting heterogeneous abnormal ship behaviors from AIS trajectories. In operational settings, DEFLT can serve as an alert-prioritization tool for vessel traffic services and port authorities by directing attention to atypical trajectories that require timely review, thereby supporting safer and more resource-efficient maritime traffic coordination.
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.
Yige Shi, Wen-yu Niu· 2026 8th International Confe...· 0 citations
Maritime Autonomous Surface Ships that are used for navigation, cargo handling and communication on a digital system. It improves operational efficiency and maximises cyber risk threats. This project is based on a framework that incorporates cybersecurity methodologies and examines dynamic data, such as geo-location coordinates, timestamps, navigation map status, performance, efficiency, cargo type, data source, and destination port, grounded in the operating unit. By leveraging Python, machine learning, and deep learning techniques, the system can easily analyse both real-time and Automatic Identification System datasets to detect anomalies linked to potential cyber threats. Anomalies are detected early, and the model supports risk mitigation and enhances autonomous maritime operations. Informed decision-making can support proactive maritime monitoring, with Automatic Identification System data features that improve accuracy and reliability. This paper proposes a hybrid model that combines LSTM and random forests to improve reliability, expandability, and predictive accuracy. The model aims to enhance the detection accuracy with techniques such as deep learning and machine learning.
Joseph Mino, M. Krishnan· DMPedia Lecture Notes in Com...· 0 citations
Vessel trajectory prediction in complex maritime environments is essential for traffic management, collision warning, route planning, and autonomous navigation. Although AIS-based learning methods have progressed rapidly, existing datasets are often released as raw message streams or irregular time series, with inconsistent sampling rates, noisy observations, heterogeneous coordinate systems, and non-unified scenario protocols. Most public AIS resources also lack structured representations of navigational lanes, waterway geometry, and navigable-region constraints, limiting reproducible, environment-aware forecasting. To address this, we introduce NaviAIS, a standardized scenario-level AIS dataset for vessel trajectory prediction. It organizes multi-vessel historical-future trajectories within unified temporal windows and local coordinate systems, and provides rasterized navigable maps, vectorized lane priors, lane graphs, and structured map representations. Compared with existing datasets, it jointly supports vectorized lanes, multi-scenario coverage, vectorized maps, open accessibility, and processed trajectories. Built on this dataset, we propose NaviLane, a hierarchical macro-action framework for map-aware prediction. NaviLane first performs trajectory-map joint encoding for a unified scene representation, then uses a discrete macro-action codebook to generate multimodal candidates coarse-to-refined. A residual refinement module improves local geometric and dynamical consistency, and a world-model-based consequence-aware evaluator ranks candidates by interaction risk and environmental feasibility. Experiments show NaviLane outperforms representative baselines in both single-modal and multimodal settings, confirming the value of structured navigational priors, hierarchical multimodal generation, and consequence-aware evaluation.
Deep learning-based vessel trajectory prediction using Automatic Identification System (AIS) has become a hot topic in the fields of maritime traffic monitoring, situational awareness, and navigational decision support. However, most previous studies have focused primarily on end-to-end model training using trajectory data from a single water area, which limits the resulting models’ ability to generalize to regions with different traffic patterns. To address this issue, this study proposes a method that constructs traffic context from historical AIS records at multiple geographic resolutions using H3, a hexagonal hierarchical spatial indexing system, and integrates this context with a Transformer-based trajectory predictor. A reliability-aware selector determines the contribution of the context to the final prediction, conditioning this decision on the vessel’s motion state and the retrieved historical patterns. Experiments on AIS data from three distinct water areas demonstrated that H3-indexed context improved cross-water prediction accuracy without requiring model retraining on the target area. These findings demonstrate that H3-indexed context, structured at multiple geographic resolutions and integrated through a selective mechanism, serves as transferable spatial context for vessel trajectory prediction.
Predicting vessel motion and environmental dynamics is essential for safe operation of autonomous maritime navigation systems. Transformer-based models have achieved strong results in AIS-trajectory forecasting and in anticipating future sonar observations, however, their use in maritime radar frame prediction has received little attention, despite radar being a key sensing modality in challenging weather and visibility conditions. In an effort to address this gap, this paper introduces a transformer architecture for predicting future maritime radar frames from sequences of past X-band observations and vessel ego-motion derived from GNSS, adapting the EchoPT paradigm originally developed for simulated in-air sonar imagery to the real-world MOANA dataset. We detail the model architecture and evaluate its prediction performance under both single-frame and autoregressive settings on held-out test data, and benchmark the model against persistence and rigid geometric warp references. A complementary failure mode analysis links the observed prediction errors to specific architectural and dataset choices, providing concrete directions for further research.
Bjorna Qesaraku, Jan Steckel· Journal of Marine Science an...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
