With the increase in global shipping volumes and the complexity of maritime transport systems, vessel trajectory prediction serves an important tool in improving maritime safety. However, most existing vessel trajectory prediction methods focus on a single feature and unable fuse high-dimensional features. To solve these problems, CNN-GRU model with a hybrid attention mechanism (AM) is proposed based on Automatic Identification System (AIS) data. First convolutional neural network (CNN) is proposed to extract the spatio-temporal information of the trajectory data. Then a gated recurrent unit (GRU) is designed to extract the temporal relationship of the trajectories. Finally, AM is introduced to learn the deep-level features and predict the vessel trajectories. To validate the effectiveness of the model, experiments are conducted on three real AIS datasets. In comparison with other models, the method has a high trajectory prediction accuracy.
ZhouYDaamenWVellingaT, et al. Review of maritime traffic models from vessel behavior modeling perspective. Transp Res Part C Emerg Technol2019; 105: 323–345.
2.
BenzLMünchCHartmannE. Development of a search and rescue framework for maritime freight shipping in the arctic. Transp Res Part A Policy Pract2021; 152: 54–69.
3.
MaDMaWHaoS, et al. Ship’s response to low-sulfur regulations: from the perspective of route, speed and refueling strategy. Comput Ind Eng2021; 155: 107140.
4.
ZhangMTaimuriGZhangJ, et al. A deep learning method for the prediction of 6-dof ship motions in real conditions. Proc IMechE, Part M: J Engineering for the Maritime Environment2023; 237(4): 887–905.
5.
ArtusiE. Ship path planning based on deep reinforcement learning and weather forecast. In: 22nd IEEE international conference on mobile data management (MDM), Toronto, Canada, 15–18 June 2021, pp.258–260. New York: IEEE.
6.
MurrayBPereraLP. An ais-based deep learning framework for regional ship behavior prediction. Reliab Eng Syst Saf2021; 215: 107819.
7.
ZhangMKujalaPMusharrafM, et al. A machine learning method for the prediction of ship motion trajectories in real operational conditions. Ocean Eng2023; 283: 114905.
8.
MurrayBPereraLP. Ship behavior prediction via trajectory extraction-based clustering for maritime situation awareness. J Ocean Eng Sci2022; 7(1): 1–13.
9.
CapobiancoSMillefioriLMFortiN, et al. Deep learning methods for vessel trajectory prediction based on recurrent neural networks. IEEE Trans Aerosp Electron Syst2021; 57(6): 4329–4346.
10.
KarataşGBKaragozPAyranO. Trajectory pattern extraction and anomaly detection for maritime vessels. Internet Things2021; 16: 100436.
11.
SvanbergMSanténVHörtebornA, et al. Ais in maritime research. Mar Policy2019; 106: 103520.
12.
ZhangMMontewkaJManderbackaT, et al. A big data analytics method for the evaluation of ship-ship collision risk reflecting hydrometeorological conditions. Reliab Eng Syst Saf2021; 213: 107674.
13.
HexebergSFlåtenALBrekkeEF, et al. Ais-based vessel trajectory prediction. In: 20th international conference on information fusion (Fusion), Xi’an, China, 10–13 July 2017, pp.1–8. IEEE.
14.
DalsnesBRHexebergSFlåtenAL, et al. The neighbor course distribution method with gaussian mixture models for ais-based vessel trajectory prediction. In: 21st international conference on information fusion (FUSION), Cambridge, 10–13 July 2018, pp.580–587. New York: IEEE.
15.
JaskólskiK. Automatic Identification System (AIS) dynamic data estimation based on discrete kalman filter (kf) algorithm. Marit Tech J2017; 211(4): 71–87.
16.
QiaoSjHanNZhuXw, et al. A dynamic trajectory prediction algorithm based on kalman filter. Acta Electon Sin2018; 46(2): 418.
17.
LiuCGuoSFengY, et al. L-vtp: long-term vessel trajectory prediction based on multi-source data analysis. Sensors2019; 19(20): 4365.
18.
GuoSLiuCGuoZ, et al. Trajectory prediction for ocean vessels base on k-order multivariate markov chain. In: Wireless Algorithms, Systems, and Applications: 13th International Conference, WASA 2018, Tianjin, China, 20–22 June 2018, pp.140–150. Cham, Switzerland: Springer.
19.
LiWZhangCMaJ, et al. Long-term vessel motion predication by modeling trajectory patterns with ais data. In: 5th international conference on transportation information and safety (ICTIS), Liverpool, 14–17 July 2019, pp.1389–1394. New York: IEEE.
20.
ZhouHChenYZhangS. Ship trajectory prediction based on bp neural network. J Artif Intell2019; 1(1): 29.
21.
ChenXWeiCZhouG, et al. Automatic identification system (ais) data supported ship trajectory prediction and analysis via a deep learning model. J Mar Sci Eng2022; 10(9): 1314.
22.
TangHYinYShenH. A model for vessel trajectory prediction based on long short-term memory neural network. J Mar Eng Technol2022; 21(3): 136–145.
23.
LiuRWLiangMNieJ, et al. Deep learning-powered vessel trajectory prediction for improving smart traffic services in maritime internet of things. IEEE Trans Netw Sci Eng2022; 9(5): 3080–3094.
24.
LiuXYuanHXiaoC, et al. Hybrid-driven vessel trajectory prediction based on uncertainty fusion. Ocean Eng2022; 248: 110836.
25.
LiuRWLiangMNieJ, et al. Stmgcn: mobile edge computing-empowered vessel trajectory prediction using spatio-temporal multigraph convolutional network. IEEE Trans Industr Inform2022; 18(11): 7977–7987.
26.
CanizoMTrigueroICondeA, et al. Multi-head cnn–rnn for multi-time series anomaly detection: an industrial case study. Neurocomputing2019; 363: 246–260.
27.
FukuokaRSuzukiHKitajimaT, et al. Wind speed prediction model using lstm and 1d-cnn. J Signal Process2018; 22(4): 207–210.
28.
XueNTrigueroIFigueredoGP, et al. Evolving deep cnn-lstms for inventory time series prediction. In: IEEE congress on evolutionary computation (CEC), Wellington, New Zealand, 10–13 June 2019, pp.1517–1524. New York: IEEE.
29.
ZhangWWuPPengY, et al. Roll motion prediction of unmanned surface vehicle based on coupled cnn and lstm. Future Internet2019; 11(11): 243.
30.
ChengXLiGEllefsenAL, et al. A novel densely connected convolutional neural network for sea-state estimation using ship motion data. IEEE Trans Instrum Meas2020; 69(9): 5984–5993.
31.
BaoKBiJGaoM, et al. An improved ship trajectory prediction based on ais data using mha-bigru. J Mar Sci Eng2022; 10(6): 804.
32.
SuoYChenWClaramuntC, et al. A ship trajectory prediction framework based on a recurrent neural network. Sensors2020; 20(18): 5133.
33.
LinJDiekmannPFramingCE, et al. Maritime environment perception based on deep learning. IEEE Trans Intell Transp Syst2022; 23(9): 15487–15497.
34.
LiYRenHLiH. Pyvt: a toolkit for preprocessing and analysis of vessel spatio-temporal trajectories. SoftwareX2023; 21: 101316.
35.
ValsamisATserpesKZissisD, et al. Employing traditional machine learning algorithms for big data streams analysis: the case of object trajectory prediction. J Syst Softw2017; 127: 249–257.
36.
DurairajDMMohanBK. A convolutional neural network based approach to financial time series prediction. Neural Comput Appl2022; 34(16): 13319–13337.
37.
ChoKVan MerriënboerBGulcehreC, et al. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:14061078, 2014.
38.
LiMWXuDYGengJ, et al. A hybrid approach for forecasting ship motion using cnn–gru–am and gcwoa. Appl Soft Comput2022; 114: 108084.
39.
ChaiTDraxlerRR. Root mean square error (rmse) or mean absolute error (mae). Geosci Model Dev Discuss2014; 7(1): 1525–1534.
40.
WangCRenHLiH. Vessel trajectory prediction based on ais data and bidirectional gru. In: International conference on computer vision, image and deep learning (CVIDL), Chongqing, China, 10–12 July 2020, pp.260–264. New York: IEEE.
41.
AdegeABLinHPWangLC. Mobility predictions for iot devices using gated recurrent unit network. IEEE Internet Things J2019; 7(1): 505–517.
