cs.LGNov 13, 2026

Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion

Authors: Daniel Grimm, Kyra Jongman, Renato Cordeiro Ferreira, Giuseppe Cascavilla, Alfredo Cuzzocrea, Willem-Jan Van Den Heuvel

Organizations: Department of Intelligent Systems, Tilburg University, Tilburg, The Netherlands · University of Calabria, Rende, Italy

Abstract

Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification System (AIS) is commonly used for this purpose, despite its known vulnerabilities. In contrast, space-based radio frequency (RF) observations provide an independent source of vessel activity but lack ship identification and therefore cannot identify vessels on their own. Following the CRISP-DM process, this study applies a Pair Hidden Markov Model (PHMM) to align individual RF detections with AIS trajectories, using temporal and spatial information while modeling noise and timing discrepancies. We evaluate it on NOAA AIS data with synthetic RF detections against nearest-neighbor baselines and analyze its errors with bias tests on trajectory length, sampling density, stationarity and AIS--RF distance. The length-corrected Forward score reaches a top-1 precision of 0.77760.7776 on the validation split of multi-candidate detections, where errors are possible, and an AUC of 0.6370.637 for detecting dark vessels among the detections that pass the prefilter. With a single RF detection, the score mostly reflects the AIS trajectory itself, and its errors favor longer and more stationary trajectories. A log-odds score, which compares the full model with a null model without match transitions, raises precision to 0.85800.8580 and AUC to 0.8520.852. Its length-corrected variant no longer shows a significant bias towards stationary trajectories and short inter-message distances, but still favors candidates farther from the RF detection. A time-weighted nearest-neighbor baseline without fitting remains ahead (precision 0.90130.9013, AUC 0.9040.904), so this single-detection, hand-designed PHMM formulation approaches but does not beat it.

Figures & tables

Explore similar work

CardsList
  1. Sea-Scan: High-Accuracy, ML-based Dark Vessel Detection and Localisation via Weakly Supervised DAS Monitoring

    Jun 19, 2026Tian Tian, Agastya Raj, Lara Flanagan +2Distributed Acoustic SensingObject Detection

  2. Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies

    Jun 29, 2026Youngseok Hwang, Sungho Bae, Dohun Lee +4Synthetic Anomaly GenerationTime-Series Anomaly Detection