Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies

2026-06-28

AI Summary

Existing maritime anomaly detection methods rely on statistical rarity or expert-defined rules, which struggle to accurately capture real-world risk—particularly in scenarios involving vessel interactions such as close encounters—and suffer from high costs, subjectivity, and poor scalability. This work proposes the first anomaly taxonomy grounded in nautical dynamics equations, defining three distinct anomaly types: AIS activity anomalies, trajectory deviations, and close encounters. It further introduces a unified framework integrating large language model (LLM)-based plausibility scoring, synthetic time-series generation, and fine-grained timestamp annotation. The resulting open evaluation benchmark enables comprehensive assessment across multiple anomaly categories, significantly improving both the detection performance for single-vessel and multi-vessel interaction anomalies and the consistency of their evaluation.

Abstract

Maritime anomaly detection is essential for ensuring maritime safety, security, and efficient traffic management at sea, with Automatic Identification System (AIS) data serving as a primary data source. Despite its importance, most publicly available AIS datasets lack predefined anomaly labels, forcing prior studies to rely on either distribution-based rarity or domain rule/expert-assisted labeling. These approaches, however, face fundamental limitations: statistical rarity often fails to reflect practically critical events, while expert-based labeling is costly, subjective, and difficult to scale. Moreover, both paradigms tend to overlook interaction-driven hazards such as near-miss approaches between vessels. To address these challenges, we propose an equation-grounded anomaly taxonomy that is implementable under a limited AIS observation schema and extensible to other AIS datasets. Specifically, the taxonomy defines three anomaly types: unexpected AIS activity (A1), route deviation (A2), and close approach (A3), covering both single-vessel and inter-vessel anomalies. Building on this taxonomy, we introduce a unified score-synthesize-label pipeline that produces LLM-guided plausibility scores, uses them to synthesize anomalies, and assigns timestamp-level labels. To rigorously assess detection performance, we further design benchmark evaluation settings that account for variations in temporal-window length and anomaly-type composition, and evaluate a broad range of time-series models and anomaly detection models. Together, these contributions provide a systematic basis for evaluating maritime anomaly detection methods across different anomaly types. Our code is available at https://github.com/snudial/open-maritime-anomaly-detection.

Problem

• maritime anomaly detection
• AIS data
• anomaly labeling
• interaction-driven hazards
• close approach

Innovation

• equation-grounded anomaly taxonomy
• synthetic anomaly generation
• maritime anomaly detection
• AIS data
• LLM-guided plausibility scoring