English

Federated Learning and Trajectory Compression for Enhanced AIS Coverage

Machine Learning 2025-12-04 v1

Abstract

This paper presents the VesselEdge system, which leverages federated learning and bandwidth-constrained trajectory compression to enhance maritime situational awareness by extending AIS coverage. VesselEdge transforms vessels into mobile sensors, enabling real-time anomaly detection and efficient data transmission over low-bandwidth connections. The system integrates the M3fed model for federated learning and the BWC-DR-A algorithm for trajectory compression, prioritizing anomalous data. Preliminary results demonstrate the effectiveness of VesselEdge in improving AIS coverage and situational awareness using historical data.

Keywords

Cite

@article{arxiv.2512.03584,
  title  = {Federated Learning and Trajectory Compression for Enhanced AIS Coverage},
  author = {Thomas Gräupl and Andreas Reisenbauer and Marcel Hecko and Anil Rasouli and Anita Graser and Melitta Dragaschnig and Axel Weissenfeld and Gilles Dejaegere and Mahmoud Sakr},
  journal= {arXiv preprint arXiv:2512.03584},
  year   = {2025}
}
R2 v1 2026-07-01T08:07:23.424Z