Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Context-Enriched Natural Language Descriptions of Vessel Trajectories

Kostas Patroumpas, Alexandros Troupiotis-Kapeliaris, Giannis Spiliopoulos, Panagiotis Betchavas, Dimitrios Skoutas, Dimitris Zissis, Nikos Bikakis

Abstract

We address the problem of transforming raw vessel trajectory data collected from AIS into structured and semantically enriched representations interpretable by humans and directly usable by machine reasoning systems. We propose a context-aware trajectory abstraction framework that segments noisy AIS sequences into distinct trips each consisting of clean, mobility-annotated episodes. Each episode is further enriched with multi-source contextual information, such as nearby geographic entities, offshore navigation features, and weather conditions. Crucially, such representations can support generation of controlled natural language descriptions using LLMs. We empirically examine the quality of such descriptions generated using several LLMs over AIS data along with open contextual features. By increasing semantic density and reducing spatiotemporal complexity, this abstraction can facilitate downstream analytics and enable integration with LLMs for higher-level maritime reasoning tasks.

Context-Enriched Natural Language Descriptions of Vessel Trajectories

Abstract

We address the problem of transforming raw vessel trajectory data collected from AIS into structured and semantically enriched representations interpretable by humans and directly usable by machine reasoning systems. We propose a context-aware trajectory abstraction framework that segments noisy AIS sequences into distinct trips each consisting of clean, mobility-annotated episodes. Each episode is further enriched with multi-source contextual information, such as nearby geographic entities, offshore navigation features, and weather conditions. Crucially, such representations can support generation of controlled natural language descriptions using LLMs. We empirically examine the quality of such descriptions generated using several LLMs over AIS data along with open contextual features. By increasing semantic density and reducing spatiotemporal complexity, this abstraction can facilitate downstream analytics and enable integration with LLMs for higher-level maritime reasoning tasks.
Paper Structure (13 sections, 8 figures, 5 tables)

This paper contains 13 sections, 8 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Constructing Context-Enriched Semantic Trajectory Representations
  4. Trajectory Annotation with Mobility Events
  5. Trajectory Segmentation in Trips and Episodes
  6. Context Enrichment
  7. Output Representations
  8. LLM-Generated Descriptions of Vessel Trips
  9. Empirical Evaluation
  10. Experimental Setup
  11. Performance Results
  12. Qualitative Assessment of Generated Descriptions
  13. Concluding Remarks

Figures (8)

  • Figure 1: Originally reported AIS locations (in black dots) of a vessel after annotation: green boxes signify stops, orange triangles denote turning points, and red stars indicate noise.
  • Figure 2: Trip representation in successive episodes with statistics (in green box) along with contextual information from various external data sources (in red box) as extracted in CSV format suitable for map visualization (MAP).
  • Figure 3: Alternative episode representations.
  • Figure 4: Prompt template for generating trajectory descriptions. The LLM receives as input a jsonarray with distilled context-enhanced representation about a vessel trip and generates: (i) semantically-rich natural language descriptions in plain text, and (ii) overall trip statistics (in jsonformat).
  • Figure 5: Trajectory episodes (depicted on map with alternating colors) given as input to LLM for generating a textual description.
  • ...and 3 more figures