Using LLMs for Analyzing AIS Data
This work provides practical guidance for researchers and practitioners in mobility data science on selecting appropriate LLM methods for AIS data analysis, though it appears incremental in nature.
This paper tackles the problem of analyzing Automatic Identification System (AIS) data by experimenting with four different LLM-based methods, finding that each approach has distinct strengths and weaknesses for specific data analysis objectives.
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.