Predicting vessel trajectories and detecting anomalous behaviors are fundamental yet challenging tasks in the maritime domain, primarily due to the dynamic and unstructured nature of the marine environment. While Spatio-Temporal Graph Neural Networks (ST-GNNs) have shown great promise in modeling relational and temporal dependencies, their reliance on fixed spatial anchors limits their applicability to maritime scenarios, where such anchors are inherently absent. To address this limitation, we propose a novel GNN-based framework, denoted as Spatio-Temporal Graph-based Vessel behavior Anomaly Detection (STGVAD), that redefines graph construction for vessel behavior modeling. Instead of relying on static spatial points, we represent each timestamped vessel state as a node and construct a unified multi-ship trajectory graph by linking temporally adjacent nodes and incorporating spatial proximity using the OPTICS clustering algorithm. This enables the joint modeling of temporal dynamics and inter-vessel interactions within a single graph structure. Our framework employs a GNN encoder to capture spatio-temporal patterns, followed by a time-series module. To support objective evaluation, we manually injected anomalies into real AIS dataset. Experimental results demonstrate that STGVAD significantly outperforms conventional time-series baselines, particularly under conditions with scarce anomalies. These findings highlight the importance of joint spatio-temporal modeling and validate the robustness and generalizability of our approach in complex maritime environments.

Ship collision risk assessment has advanced over recent years, enhancing maritime safety. However, existing studies often describe ship domains and collision risk assessments in a static manner, lacking interactivity. Interactive visualization of collision risk, especially in multi-ship scenarios has not been sufficiently developed. This gap prompted the development of “FURIOUS: Fully Unified Risk-assessment with Interactive Operational User System for vessels.” This tool aids in visualizing and analyzing collision risk of multi-ship encounter situation through real-time visualization. Our system processes data from Automatic Identification System (AIS). The system performs ship domain calculations and collision risk assessments supported by geographical computations, and includes features like real-time vessel display and collision type detection. Interactive and user-selectable elements, along with dynamic maps enhance real-time decision-making to ensure navigation safety. Additionally, the system aids both experienced and novice users in understanding complicated maritime dynamic environments. Users can adjust parameters like ship type, ship IDs, time window and map type for tailored analyses and proactive collision avoidance. We conducted a user study to validate these features, confirming that they effectively improve situational awareness and enhance decision-making capabilities in real-world scenarios. This paper details the design, implementation, and evaluation of this tool, highlighting its potential to transform maritime decision-making by improving situational awareness and enhancing operational efficiency.

With the increase in maritime traffic and the mandatory implementation of the Automatic Identification System (AIS), the importance and diversity of maritime traffic analysis tasks based on AIS data, such as vessel trajectory prediction, anomaly detection, and collision risk assessment, is rapidly growing. However, existing approaches tend to address these tasks individually, making it difficult to holistically consider complex maritime situations. To address this limitation, we propose a novel framework, AIS-LLM, which integrates time-series AIS data with a large language model (LLM). AIS-LLM consists of a Time-Series Encoder for processing AIS sequences, an LLM-based Prompt Encoder, a Cross-Modality Alignment Module for semantic alignment between time-series data and textual prompts, and an LLM-based Multi-Task Decoder. This architecture enables the simultaneous execution of three key tasks: trajectory prediction, anomaly detection, and risk assessment of vessel collisions within a single end-to-end system. Experimental results demonstrate that AIS-LLM outperforms existing methods across individual tasks, validating its effectiveness. Furthermore, by integratively analyzing task outputs to generate situation summaries and briefings, AIS-LLM presents the potential for more intelligent and efficient maritime traffic management.