Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning
Authors: 
Pierre Bernabé, Arnaud Gotlieb, Bruno Legeard, Dusica Marijan, Frank Olaf Sem-Jacobsen, Helge SpiekerAuthors Info & Claims
Pierre Bernabé, Arnaud Gotlieb, Bruno Legeard, Dusica Marijan, Frank Olaf Sem-Jacobsen, Helge SpiekerAuthors Info & ClaimsPages 1166 - 1177
Abstract
In maritime traffic surveillance, detecting illegal activities, such as illegal fishing or transshipment of illicit products is a crucial task of the coastal administration. In the open sea, one has to rely on Automatic Identification System (AIS) message transmitted by on-board transponders, which are captured by surveillance satellites. However, insincere vessels often intentionally shut down their AIS transponders to hide illegal activities. In the open sea, it is very challenging to differentiate intentional AIS shutdowns from missing reception due to protocol limitations, bad weather conditions or restricting satellite positions. This paper presents a novel approach for the detection of abnormal AIS missing reception based on self-supervised deep learning techniques and transformer models. Using historical data, the trained model predicts if a message should be received in the upcoming minute or not. Afterwards, the model reports on detected anomalies by comparing the prediction with what actually happens. Our method can process AIS messages in real-time, in particular, more than 500 Millions AIS messages per month, corresponding to the trajectories of more than 60 000 ships. The method is evaluated on 1-year of real-world data coming from four Norwegian surveillance satellites. Using related research results, we validated our method by rediscovering already detected intentional AIS shutdowns.
References
[1]
M. Riveiro, G. Pallotta, and M. Vespe, “Maritime anomaly detection: A review,” WIREs Data Mining Knowl. Discovery, vol. 8, no. 5, Sep. 2018, Art. no.
[2]
“Revised guidelines for the onboard operational use of shipborne automatic identification systems (AIS),” IMO, Int. Maritime Org. (IMO), London, U.K., Tech. Rep. Resolution A.1106(29), 2015.
[3]
L. Malarky and B. Lowell, “Avoiding detection: Global case studies of possible AIS avoidance,” OCEANA, Washington, DC, USA, Tech. Rep., Mar. 2018. [Online]. Available: https://oceana.org/publications/reports/avoiding-detection-global-case-studies-possible-ais-avoidance
[4]
P. Mustain, “Now you see me, now you don’t: Vanishing vessels along Argentina’s waters,” OCEANA, Washington, DC, USA, Tech. Rep., Jun. 2021. [Online]. Available: https://usa.oceana.org/publications/reports/oceana-finds-hundreds-vessels-vanishing-along-argentinas-waters. 10.5281/zenodo.4893397.
[5]
D. J. Agnewet al., “Estimating the worldwide extent of illegal fishing,” PLoS ONE, vol. 4, no. 2, Feb. 2009, Art. no.
[6]
R. M. Desai and G. E. Shambaugh, “Measuring the global impact of destructive and illegal fishing on maritime piracy: A spatial analysis,” PLoS ONE, vol. 16, no. 2, Feb. 2021, Art. no.
[7]
L. Ericsson, H. Gouk, C. C. Loy, and T. M. Hospedales, “Self-supervised representation learning: Introduction, advances, and challenges,” IEEE Signal Process. Mag., vol. 39, no. 3, pp. 42–62, May 2022.
[8]
F. Mazzarella, M. Vespe, A. Alessandrini, D. Tarchi, G. Aulicino, and A. Vollero, “A novel anomaly detection approach to identify intentional AIS on-off switching,” Expert Syst. Appl., vol. 78, pp. 110–123, Jul. 2017.
[9]
F. Mazzarella, M. Vespe, D. Tarchi, G. Aulicino, and A. Vollero, “AIS reception characterisation for AIS on/off anomaly detection,” in Proc. 19th Int. Conf. Inf. Fusion (FUSION), Jul. 2016, pp. 1867–1873.
[10]
A. Y. Shahir, M. A. Tayebi, U. Glässer, T. Charalampous, Z. Zohrevand, and H. Wehn, “Mining vessel trajectories for illegal fishing detection,” in Proc. IEEE Int. Conf. Big Data (Big Data), Dec. 2019, pp. 1917–1927.
[11]
I. Kontopoulos, K. Chatzikokolakis, D. Zissis, K. Tserpes, and G. Spiliopoulos, “Real-time maritime anomaly detection: Detecting intentional AIS switch-off,” Int. J. Big Data Intell., vol. 7, no. 2, pp. 85–96, 2020.
[12]
S. Singh and F. Heymann, “Machine learning-assisted anomaly detection in maritime navigation using AIS data,” in Proc. IEEE/ION Position, Location Navigat. Symp. (PLANS), Apr. 2020, pp. 832–838.
[13]
J. H. Fordet al., “Detecting suspicious activities at sea based on anomalies in automatic identification systems transmissions,” PLoS One, vol. 13, no. 8, 2018, Art. no.
[14]
H. Weimerskirchet al., “Ocean sentinel albatrosses locate illegal vessels and provide the first estimate of the extent of nondeclared fishing,” Proc. Nat. Acad. Sci. USA, vol. 117, no. 6, pp. 3006–3014, Feb. 2020.
[15]
E. d’Afflisio, P. Braca, L. M. Millefiori, and P. Willett, “Detecting anomalous deviations from standard maritime routes using the Ornstein–Uhlenbeck process,” IEEE Trans. Signal Process., vol. 66, no. 24, pp. 6474–6487, Dec. 2018.
[16]
J. Parket al., “Illuminating dark fishing fleets in North Korea,” Sci. Adv., vol. 6, no. 30, Jul. 2020, Art. no.
[17]
B. R. Dalsnes, S. Hexeberg, A. L. Flaten, B. H. Eriksen, and E. F. Brekke, “The neighbor course distribution method with Gaussian mixture models for AIS-based vessel trajectory prediction,” in Proc. 21st Int. Conf. Inf. Fusion (FUSION), Jul. 2018, pp. 580–587.
[18]
B. Ristic, “Detecting anomalies from a multitarget tracking output,” IEEE Trans. Aerosp. Electron. Syst., vol. 50, no. 1, pp. 798–803, Jan. 2014.
[19]
N. Fridman, D. Amir, Y. Douchan, and N. Agmon, “Satellite detection of moving vessels in marine environments,” in Proc. AAAI, vol. 33, 2019, pp. 9452–9459.
[20]
K.-I. Kim and K. Lee, “Deep learning-based caution area traffic prediction with automatic identification system sensor data,” Sensors, vol. 18, no. 9, p. 3172, Sep. 2018.
[21]
D. D. Bloisi, F. Previtali, A. Pennisi, D. Nardi, and M. Fiorini, “Enhancing automatic maritime surveillance systems with visual information,” IEEE Trans. Intell. Transp. Syst., vol. 18, no. 4, pp. 824–833, Apr. 2017.
[22]
V. F. Arguedas, G. Pallotta, and M. Vespe, “Maritime traffic networks: From historical positioning data to unsupervised maritime traffic monitoring,” IEEE Trans. Intell. Transp. Syst., vol. 19, no. 3, pp. 722–732, Mar. 2018.
[23]
D. Nguyen, R. Vadaine, G. Hajduch, R. Garello, and R. Fablet, “A multi-task deep learning architecture for maritime surveillance using AIS data streams,” in Proc. IEEE 5th Int. Conf. Data Sci. Adv. Anal. (DSAA). IEEE, Oct. 2018, pp. 331–340.
[24]
D. Nguyen, R. Vadaine, G. Hajduch, R. Garello, and R. Fablet, “GeoTrackNet—A maritime anomaly detector using probabilistic neural network representation of AIS tracks and a contrario detection,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 6, pp. 5655–5667, Jun. 2022.
[25]
A. N. Skauen, “Ship tracking results from state-of-the-art space-based AIS receiver systems for maritime surveillance,” CEAS Space J., vol. 11, no. 3, pp. 301–316, Sep. 2019.
[26]
Technical Characteristics for an Automatic Identification System Using Time Division Multiple Access in the VHF Maritime Mobile Frequency Band, document Recommendation ITU-R M.1371-5, ITU-R Radiocommunication Sector of the International Telecommunication Union, 2014. [Online]. Available: https://www.itu.int/rec/R-REC-M.1371-5-201402-I
[27]
T. Eriksen, G. Høye, B. Narheim, and B. J. Meland, “Maritime traffic monitoring using a space-based AIS receiver,” Acta Astronautica, vol. 58, no. 10, pp. 537–549, May 2006.
[28]
A. N. Skauen, “Quantifying the tracking capability of space-based AIS systems,” Adv. Space Res., vol. 57, no. 2, pp. 527–542, Jan. 2016.
[29]
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics (NAACL), 2019, pp. 4171–4186.
[30]
A. Dosovitskiyet al., “An image is worth 16×16 words: Transformers for image recognition at scale,” in Proc. ICLR, 2020, pp. 1–21.
[31]
S. Liet al., “Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting,” in Proc. Adv. Neural Inf. Syst. (NeurIPS), vol. 32, 2019, pp. 1–11.
[32]
B. Lim and S. Zohren, “Time-series forecasting with deep learning: A survey,” Phil. Trans. Roy. Soc. A: Math., Phys. Eng. Sci., vol. 379, no. 2194, 2021, Art. no.
[33]
D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” 2016, arXiv:1409.0473.
[34]
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997.
[35]
A. Vaswaniet al., “Attention is All you Need,” in Proc. Adv. Neural Inf. Syst. (NeurIPS), 2017, pp. 1–11.
[36]
J. Cheng, L. Dong, and M. Lapata, “Long short-term memory-networks for machine reading,” in Proc. Conf. Empirical Methods Natural Lang. Process., 2016, pp. 1–11.
[37]
J. Quinonero-Candela, M. Sugiyama, A. Schwaighofer, N. D. Lawrence, M. I. Jordan, and T. G. Dietterich, Eds., Dataset Shift in Machine Learning (Neural Information Processing Series). Cambridge, MA, USA: MIT Press, 2008.
Index Terms
- Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning
Index terms have been assigned to the content through auto-classification.
Recommendations
Maritime surveillance
Research highlights Existing vision-based tracking methods are not suitable for the maritime domain. We derive a suitable tracking method by combining and modifying existing methods. Our method can track tiny targets. Our method is validated on several ...
Passive Maritime Surveillance Based on Low Earth Orbit Satellite Constellations
The rapid growth of maritime transportation and its regularization have imposed an increasing demand for developing a global maritime surveillance capacity. The existing cooperative maritime traffic monitoring relies on the shipborne automatic ...
A novel anomaly detection approach to identify intentional AIS on-off switching
An anomaly detection algorithm to identify AIS on-off switching is proposed.The algorithm exploits the AIS message Received Signal Strength Indicator.Machine Learning algorithms are used to build normality models.AIS reception is characterized by using ...
Comments
Information & Contributors
Information
Published In
1558-0016 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Press
Publication History
Published: 17 October 2023
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 04 Oct 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in