# Context-Enriched Natural Language Descriptions of Vessel Trajectories

Source: [Context-Enriched Natural Language Descriptions of Vessel Trajectories](<https://www.sota2.com/research/paper/69b78e8f0636e5bf4afbdbe0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-17T05:00:04.157Z

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

Published: 2026-03-08T15:17:25.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Narrative Generation on vessel trip descriptions (test)](<https://www.sota2.com/research/sota/narrative-generation-on-vessel-trip-descriptions-test.md>): Narrative Generation; vessel trip descriptions (test); Relevance: not recorded.

- [Travelled distance estimation on Vessel Trajectory Descriptions](<https://www.sota2.com/research/sota/travelled-distance-estimation-on-vessel-trajectory-descriptions.md>): Travelled distance estimation; Vessel Trajectory Descriptions; Mean Error (%): not recorded.

- [Response Time Measurement on AIS dataset (Trip description generation)](<https://www.sota2.com/research/sota/response-time-measurement-on-ais-dataset-trip-description-generation.md>): Trip description generation; AIS dataset; Response Time (s): not recorded.

- [Trip duration estimation on vessel trajectory dataset](<https://www.sota2.com/research/sota/trip-duration-estimation-on-vessel-trajectory-dataset.md>): Trip duration estimation; vessel trajectory dataset; Mean Error: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.12287>)

[PDF](<https://arxiv.org/pdf/2603.12287.pdf>)
