Based on real-time position tracking recognition and trajectory prediction analysis of ships, dynamic control and route planning of maritime traffic are achieved, and a ship operation trajectory prediction method based on Bayesian optimization is proposed. A parameter model for ship trajectories is built based on original samples such as position, velocity, and heading. The point information of the ship’s current position is used to constrain the maximum deviations of heading and velocity. A kernel density estimation model is used to summarize and infer the historical trajectory of the ship, revealing hidden relationships. In the Bayesian estimation model, historical ship trajectory data and trajectory features are used as inputs, and an adaptive dynamic weighting method is used for training as autocorrelation feature quantities for predicting different types of ship trajectories. A grid clustering method is used to cluster ship trajectories and predict the trajectories of selected categories of ships. The simulation results show that this method can effectively predict the safe navigation area of ships, with an average error of 2.8 kilometers after 4 hours of prediction. It does not require iterative weighting and bias, and is more suitable for shipping safety related application scenarios such as collision avoidance.

Li Weibo, Yang Dawei, Wang Zixuan. Simulation study on ship operation trajectory prediction based on Bayesian optimization. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 8: 90-97. https://doi.org/10.25236/AJCIS.2026.090811.

[1] JIANG Lingling. Research on Ship Movement Trajectory Tracking at Sea Assisted by 3D Computer Navigation [J]. Ship Science and Technology,2025,47(06):154-157.

[2] Wang Ziming, Chen Shunhuai, Zheng Long. Dynamic collision avoidance trajectory planning for unmanned ships based on improved PRM algorithm and event triggering mechanism [J]. Ship mechanics,2025,29(08):1239-1249.

[3] Jin Xiaodi. Finite time learning control for ship trajectory tracking [J]. Ship engineering, 2025,47(07):107-111.

[4] Zhu Mengwei. Application of VR Virtual Reality Technology in Ship Navigation Trajectory [J]. Ship Science and Technology,2019,41(22):31-33.

[5] Capobianco S, Millefiori L M, Forti N, et al. Deep learning methods for vessel trajectory prediction based on recurrent neural networks[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(6): 4329-4346.

[6] Kim K I, Lee K M. Deep learning-based caution area traffic prediction with automatic identification system sensor data[J]. Sensors, 2018, 18(9): 3172.

[7] Last P, Hering-Bertram M, Linsen L. Interactive history-based vessel movement prediction[J]. IEEE Intelligent Systems, 2019, 34(6): 3-13.

[8] Volkova T A, Balykina Y E, Bespalov A. Predicting ship trajectory based on neural networks using AIS data[J]. Journal of Marine Science and Engineering, 2021, 9(3): 254.

[9] Chen X, Ling J, Yang Y, et al. Ship trajectory reconstruction from AIS sensory data via data quality control and prediction[J]. Mathematical Problems in Engineering, 2020, 2020: 1-9.

[10] Jin Hao. Ship trajectory prediction based on multi-scale LSTM Attention [J]. Ship electrical technology,2025,45(07):76-81.