Using LLMs for Analyzing AIS Data

2025-04-10

AI Summary

This work addresses the insufficient evaluation of large language models’ (LLMs) reasoning capabilities in spatiotemporal analysis of Automatic Identification System (AIS) data. We conduct the first systematic comparison of four inference paradigms: natural-language interfaces, raw-data reasoning, compressed-trajectory reasoning, and semantic-trajectory reasoning. To bridge this gap, we propose a novel semantic-trajectory reasoning framework tailored to maritime scenarios, integrating vessel state recognition (anchoring vs. sailing) with trajectory semantic modeling. Our approach unifies LLaMA/GPT-family LLMs, spatial database interfaces, and the Douglas–Peucker trajectory compression algorithm. Experiments demonstrate that semantic-trajectory reasoning achieves significantly higher accuracy and interpretability than alternative paradigms; meanwhile, natural-language interfaces enable zero-code spatial querying. We further establish a method-selection guidance framework, providing the first empirical benchmark and reusable best-practice guidelines for AI-driven maritime analytics.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recent research in Large Language Models (LLMs), has had a profound impact across various fields, including mobility data science. This paper explores the and experiment with different approaches to using LLMs for analyzing AIS data. We propose a set of carefully designed queries to assess the reasoning capabilities of LLMs in this kind of tasks. Further, we experiment with four different methods: (1) using LLMs as a natural language interface to a spatial database, (2) reasoning on raw data, (3) reasoning on compressed trajectories, and (4) reasoning on semantic trajectories. We investigate the strengths and weaknesses for the four methods, and discuss the findings. The goal is to provide valuable insights for both researchers and practitioners on selecting the most appropriate LLM-based method depending on their specific data analysis objectives.

Problem

• Exploring LLMs for analyzing AIS mobility data
• Assessing LLM reasoning on raw and processed trajectories
• Comparing four LLM methods for optimal data analysis

Innovation

• LLMs as natural language interface
• Reasoning on raw AIS data
• Semantic trajectory analysis with LLMs