AIS-LLM: A Unified Framework for Maritime Trajectory Prediction, Anomaly Detection, and Collision Risk Assessment with Explainable Forecasting

2025-08-11

AI Summary

Existing maritime traffic analysis methods are predominantly single-task oriented, hindering synergistic modeling of trajectory prediction, anomaly detection, and collision risk assessment—thus limiting comprehensive situational understanding under complex maritime conditions. This paper proposes the first end-to-end multi-task framework integrating temporal AIS data with large language models (LLMs). It employs a temporal encoder to extract dynamic navigational features, an LLM-based prompt encoder for semantic guidance, a cross-modal alignment module to fuse heterogeneous representations, and a unified multi-task decoder that jointly outputs predictions, anomaly detections, and risk assessments—while generating interpretable natural-language situational reports. Experiments demonstrate significant performance gains over state-of-the-art baselines across all tasks, achieving both high accuracy and strong interpretability. The framework establishes a novel paradigm for intelligent maritime management.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

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.

Problem

• Unified maritime trajectory prediction, anomaly detection, and collision risk assessment
• Integrating AIS data with LLM for holistic maritime analysis
• Improving maritime traffic management through explainable multi-task learning

Innovation

• Integrates AIS data with large language model
• Uses cross-modality alignment for semantic integration
• End-to-end multi-task decoder for maritime tasks