VISTA: Knowledge-Driven Interpretable Vessel Trajectory Imputation via Large Language Models

2026-01-11

arXiv.org

AI Summary

This work addresses the challenge of missing data in Automatic Identification System (AIS) trajectories, which often results from signal loss or intentional interference and hinders downstream maritime applications. To overcome the limitations of existing interpolation methods—particularly their lack of interpretability and limited utility for subsequent tasks—the authors propose VISTA, a novel framework that integrates structured knowledge graphs with the implicit knowledge of large language models to establish a closed-loop “data–knowledge–data” mechanism for interpretable trajectory interpolation. VISTA incorporates a parallelized workflow architecture that substantially enhances computational efficiency for large-scale processing. Evaluated on two real-world AIS datasets, VISTA achieves interpolation accuracy improvements of 5% to 94% over state-of-the-art methods while reducing computation time by 51% to 93%, and it generates interpretable knowledge cues that effectively support downstream tasks such as anomaly detection and route planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The Automatic Identification System provides critical information for maritime navigation and safety, yet its trajectories are often incomplete due to signal loss or deliberate tampering. Existing imputation methods emphasize trajectory recovery, paying limited attention to interpretability and failing to provide underlying knowledge that benefits downstream tasks such as anomaly detection and route planning. We propose knowledge-driven interpretable vessel trajectory imputation (VISTA), the first trajectory imputation framework that offers interpretability while simultaneously providing underlying knowledge to support downstream analysis. Specifically, we first define underlying knowledge as a combination of Structured Data-derived Knowledge (SDK) distilled from AIS data and Implicit LLM Knowledge acquired from large-scale Internet corpora. Second, to manage and leverage the SDK effectively at scale, we develop a data-knowledge-data loop that employs a Structured Data-derived Knowledge Graph for SDK extraction and knowledge-driven trajectory imputation. Third, to efficiently process large-scale AIS data, we introduce a workflow management layer that coordinates the end-to-end pipeline, enabling parallel knowledge extraction and trajectory imputation with anomaly handling and redundancy elimination. Experiments on two large AIS datasets show that VISTA is capable of state-of-the-art imputation accuracy and computational efficiency, improving over state-of-the-art baselines by 5%-94% and reducing time cost by 51%-93%, while producing interpretable knowledge cues that benefit downstream tasks. The source code and implementation details of VISTA are publicly available.

Problem

• trajectory imputation
• interpretability
• Automatic Identification System
• knowledge-driven
• maritime navigation

Innovation

• knowledge-driven imputation
• interpretable trajectory recovery
• structured knowledge graph
• large language models
• AIS data processing