Les commentaires sont clos.

PhD position: Robust satellite AIS receivers based on signal classification techniques for dense maritime traffic areas

17 Janvier 2022

Catégorie : Doctorant


Low-earth orbit (LEO) satellites, Internet of Things (IoT), interference management, classification, machine learning, neural network, selective channel



Karine Amis, Frédéric Guilloud (IMT Atlantique, Brest campus)

(karine.amis and frederic.guilloud at


CNRS UMR 6285 - Lab-STICC / T2I3 / Cosyde




Fall 2022 – Fall 2025


Application deadline

31st march 2022.

Application procedure

Apply online on



The AIS system enables automatic identification between ships. Its primary objective is to reduce collision risks. Thanks to its large-scale deployment, a precise real time knowledge of the sea traffic has come up on the coastal areas. Indeed, the range of the AIS signal is limited to avoid any message collision within the self-organized time-division multiple access.

Recently, low earth orbit satellite constellations enable to extend the maritime traffic knowledge to off-shore regions, opening therefore new commercial opportunities and leading the AIS standard (4th version) to add 2 new frequencies dedicated to long-range transmissions.

Problems and objectives of the thesis

The reception of AIS signals by LEO satellites is difficult for at least two main reasons: the first one is the propagation channel (low signal-to-noise ratio, doppler shift) and the second one is the wide geographical coverage which includes several AIS cells, especially when the traffic is dense, thus inducing AIS message collisions at the satellite side.

Contributions have been proposed to cope with these issues, including advanced detection, synchronization [3,4], demodulation algorithms [5,6] and multiple antenna processing [2]. However, improvements in the message detection probabilities are limited by interferences coming from the field of view [1]. These interferences consist not only of AIS collisions, but also of other sources coming from various terrestrial VHF communications. Many contributions are concerned with interference mitigations. For example, adaptive interference suppression techniques based on array signal processing have been widely studied: they assume though the possibility of an array of antennas. Since for AIS signals, beamforming capabilities are limited by the shape, the size and the number of antennas handled by the satellite, space-time techniques have been proposed [7,8] followed by their reduced-complexity counterpart [9]. Regarding the reduced number of AIS antennas capability onboard, techniques as in [10] could be investigated where interferences are discarded even when in the same direction as the signal of interest, provided they be narrow band with respect to the signal of interest.

The identification of the main characteristics of AIS interferences received at the satellite side would help to improve the robustness of the AIS receiver and lower the fluctuations of the AIS message detection and demodulation rate. Machine learning could be investigated to serve that purpose but other classification techniques should also be investigated. Using identified features of interferences could help interference suppression by using an ad-hoc algorithm while keeping the complexity reasonably low enough for onboard processing by either reducing the processing complexity or by choosing to dedicate the processing power to a specific signal of interest.


Expected Contributions of the Thesis

  • ·State of the art of adaptive interference suppression techniques, and their compatibility with antenna constraints on AIS frequencies onboard satellites.
  • ·Proposition of a classification of possible various VHF interferences and jammers
  • ·Automatic interferences classification with the help of machine learning
  • ·Proposition of robust detection / demodulation algorithms taking into account the characteristic knowledge of the received interference.
  • ·Extension of the contributions to real-time signals

Student profile: engineering school / master 2 degree in signal processing


On-line Application:


[1] Skauen, A.N. Ship tracking results from state-of-the-art space-based AIS receiver systems for maritime surveillance. CEAS Space J11, 301–316 (2019).

[2] M. Picard, M. R. Oularbi, G. Flandin and S. Houcke, "An adaptive multi-user multi-antenna receiver for satellite-based AIS detection," 2012 6th Advanced Satellite Multimedia Systems Conference (ASMS) and 12th Signal Processing for Space Communications Workshop (SPSC), 2012, pp. 273-280, doi: 10.1109/ASMS-SPSC.2012.6333088.

[3] K. Nozaki, Y. Takanezawa, Y. Chang, K. Fukawa and D. Hirahara, "Multiuser Detection of Collided AIS Packets with Accurate Estimates of Doppler Frequencies," 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 2021, pp. 1-5, doi: 10.1109/VTC20

[4] W. Lan et al., "A pipelined synchronization approach for satellite-based automatic identification system," 2016 IEEE International Conference on Communications (ICC), 2016, pp. 1-6, doi: 10.1109/ICC.2016.7511270.

[5] PRÉVOST, Raoul, et al. "Utilisation partielle du CRC pour la correction d’erreurs des signaux AIS reçus par satellite." Proc. Groupement de Recherche en Traitement du Signal et des Images (GRETSI), September 8-11, 2015.

[6] Malek Messai, Colavolpe Giulio, Karine Amis Cavalec, Frédéric Guilloud. Robust Detection of Binary CPMs With Unknown Modulation Index. IEEE Communications Letters, Institute of Electrical and Electronics Engineers, 2015, 19 (3), pp.339 - 342. ⟨10.1109/LCO

[7] J. Xu, S. Zhu and G. Liao, "Space-Time-Range Adaptive Processing for Airborne Radar Systems," in IEEE Sensors Journal, vol. 15, no. 3, pp. 1602-1610, March 2015, doi: 10.1109/JSEN.2014.2364594.

[8] H. Zhao, Y. Shi, B. Zhang and M. Shi, "Analysis and simulation of interference suppression for space-time adaptive processing," 2014 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), 2014, pp. 724-727, doi: 10.1109/ICSPCC.2014.6986291.

[9] Z. Duan, Y. Li and S. Xu, "Multiple signal detection based on spatial-frequency adaptive processing using fast subspace decomposition method," 2015 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), 2015, pp. 1-4, doi: 10.1109/ICSPCC.2015.7338961.

[10] M. Zhao, H. Zhao, W. Guo and Y. Tang, "An Interference Suppression Method Based on Space-Eigen Adaptive Processing for Satellite Communications," 2020 IEEE/CIC International Conference on Communications in China (ICCC), 2020, pp. 723-728, doi: 10.1109/ICC