Ship Maritime Trajectory Prediction Method Integrating Data Quality Enhancement and Spatio-Temporal Information Encoding Network
SHI Yue1,2, LUO He1,2,3, JIANG Ruhao4, WANG Guoqiang1,2,3
1. School of Management, Hefei University of Technology, Hefei 230009; 2. Key Laboratory of Process Optimization and Intelligent Decision-Making of Ministry of Education, Hefei University of Technology, Hefei 230009; 3. Anhui Province Engineering Research Center for Intelligent Management of Aerospace System, Hefei University of Technology, Hefei 230009; 4. College of Electronic Engineering, National University of Defense Technology, Hefei 230037
Abstract High-precision maritime vessel trajectory prediction is crucial for reducing collision risks and enhancing search and rescue efficiency. The dynamic maritime environment renders vessel trajectory data highly complex in both temporal and spatial dimensions. Existing methods exhibit insufficient attention to the quality and movement information of vessel trajectory data, making it challenging to fully capture the spatio-temporal features and correlations effectively. To address these issues, a ship maritime trajectory prediction method integrating data quality enhancement and spatio-temporal information encoding network(DQE-STIEN) is proposed. First, based on the characteristics of vessel trajectory data, a data quality enhancement algorithm is designed by combining hash mapping classification and local outlier factor-based anomaly detection using hash values to improve the quality of problematic data. Then, a spatio-temporal information encoding network with dual encoding channels is tailored for multi-attribute vessel trajectory data to extract and integrate positional information and movement features comprehensively. Finally, the spatio-temporal associations within the data are encoded and decoded to generate complete trajectory prediction results. Experimental results on AIS datasets from five different regions demonstrate the superior performance of DQE-STIEN. Moreover, DQE-STIEN exhibits certain generalizability, making itself effective for analyzing time-series data across various fields such as energy, sales, environment and finance.
Fund:General Project of National Natural Science Foundation of China(No.71971075,72271076,71871079), Natural Science Foundation of Anhui Province(No.2308085QG233)
Corresponding Authors:
WANG Guoqiang, Ph.D., associate professor. His research interests include multi-platform collaborative optimization and intelligent decision-making.
About author:: SHI Yue, Ph.D. candidate. His research interests include moving target trajectory prediction and low-orbit satellite network mission planning. LUO He, Ph.D., professor. His research interests include multi-subject collaborative opti-mization and intelligent decision-making. JIANG Ruhao, Ph.D., lecturer. His research interests include multi-UAV mission planning.
[1] TSOLAKIS A, NEGENBORN R R, REPPA V, et al. Model Predictive Trajectory Optimization and Control for Autonomous Surface Vessels Considering Traffic Rules. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(8): 9895-9908. [2] HUANG Y J, DU J T, YANG Z R, et al. A Survey on Trajectory-Prediction Methods for Autonomous Driving. IEEE Transactions on Intelligent Vehicles, 2022, 7(3): 652-674. [3] HU H Y, WANG Q, ZHANG Z G, et al. Holistic Transformer: A Joint Neural Network for Trajectory Prediction and Decision-Making of Autonomous Vehicles. Pattern Recognition, 2023, 141. DOI: 10.1016/j.patcog.2023.109592. [4] PARK J, JEONG J, PARK Y.Ship Trajectory Prediction Based on Bi-LSTM Using Spectral-Clustered AIS Data. Journal of Marine Science and Engineering, 2021, 9(9). DOI: 10.3390/jmse9091037. [5] ZHANG X C, FU X J, XIAO Z, et al. Vessel Trajectory Prediction in Maritime Transportation: Current Approaches and Beyond. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 19980-19998. [6] CHONDRODIMA E, PELEKIS N, PIKRAKIS A, et al. An Effici-ent LSTM Neural Network-Based Framework for Vessel Location Forecasting. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(5): 4872-4888. [7] XIAO Y, LI X C, YIN J J, et al. Adaptive Multi-Source Data Fusion Vessel Trajectory Prediction Model for Intelligent Maritime Tra-ffic. Knowledge-Based Systems, 2023, 277. DOI: 10.1016/j.knosys.2023.110799. [8] YUAN H Y, LIU Y Q, HUANG L D, et al. Real-Time Detection of Urban Gas Pipeline Leakage Based on Machine Learning of IoT Time-Series Data. Measurement, 2025, 242. DOI: 10.1016/j.measurement.2024.115937. [9] 王雨晨,邱士远,李培培,等.基于核极限学习机的多标签数据流半监督在线分类方法.模式识别与人工智能, 2024, 37(8): 741-754. (WANG Y C, QIU S Y, LI P P, et al. Semi-Supervised Online Classification Method for Multi-Label Data Stream Based on a Kernel Extreme Learning Machine. Pattern Recognition and Artificial Inte-lligence, 2024, 37(8): 741-754.) [10] 刘一达,丁小欧,王宏志,等.人工参与的迭代式数据清洗方法研究.大数据, 2023, 9(4): 59-68. (LIU Y D, DING X O, WANG H Z, et al. Research on Iterative Data Cleaning of Human-Computer Interaction. Big Data Research, 2023, 9(4): 59-68.) [11] POKOU F, SADEFO K J, BENHMAD F.Hybridization of ARIMA with Learning Models for Forecasting of Stock Market Time Series. Computational Economics, 2024, 63(4): 1349-1399. [12] LUZIA R, RUBIO L, VELASQUEZ C E.Sensitivity Analysis for Forecasting Brazilian Electricity Demand Using Artificial Neural Networks and Hybrid Models Based on Autoregressive Integrated Moving Average. Energy, 2023, 274. DOI: 10.1016/j.energy.2023.127365 [13] BAGHERI M, MCKENNEY S, WARE J G, et al. Deep Learning Models for Predicting Plant Uptake of Emerging Contaminants by Including the Role of Plant Macromolecular Compositions. Journal of Hazardous Materials, 2024, 480. DOI: 10.1016/j.jhazmat.2024.135921. [14] XU H, YANG B, LIU X K.Reverse-Graph Enhanced Graph Neural Networks for Session-Based Recommendation. Expert Systems with Applications, 2024, 245. DOI: 10.1016/j.eswa.2023.122995. [15] SHI J S, GAO P, SMOLIC A.Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token. IEEE Transactions on Multimedia, 2024, 26: 4641-4651. [16] XIE B, CAO J L, ANWER R M, et al. Multi-query and Multi-le-vel Enhanced Network for Semantic Segmentation. Pattern Recogni-tion, 2024, 156. DOI: 10.1016/j.patcog.2024.110777. [17] ZHANG J S, LI X, TIAN J L, et al. An Integrated Multi-head Dual Sparse Self-Attention Network for Remaining Useful Life Prediction. Reliability Engineering and System Safety, 2023, 233. DOI: 10.1016/j.ress.2023.109096. [18] RAY S, LAMA A, MISHRA P, et al. An ARIMA-LSTM Model for Predicting Volatile Agricultural Price Series with Random Forest Technique. Applied Soft Computing, 2023, 149. DOI: 10.1016/j.asoc.2023.110939. [19] LI H H, JIAO H, YANG Z L.Ship Trajectory Prediction Based on Machine Learning and Deep Learning: A Systematic Review and Methods Analysis. Engineering Applications of Artificial Intelligence, 2023, 126. DOI: 10.1016/j.engappai.2023.107062. [20] CHEN P, WEI L, MENG F F, et al. Vehicle Trajectory Reconstruction for Signalized Intersections: A Hybrid Approach Integrating Kalman Filtering and Variational Theory. Transportmetrica B(Transport Dynamics), 2021, 9(1): 22-41. [21] ZHANG W B, JIANG W Y, LIU Q, et al. AIS Data Repair Model Based on Generative Adversarial Network. Reliability Engineering and System Safety, 2023, 240. DOI: 10.1016/j.ress.2023.109572. [22] RONG H, TEIXEIRA A P, SOARES C G.Maritime Traffic Probabilistic Prediction Based on Ship Motion Pattern Extraction. Reliability Engineering and System Safety, 2022, 217. DOI: 10.1016/j.ress.2021.108061. [23] ABEBE M, NOH Y, KANG Y J, et al. Ship Trajectory Planning for Collision Avoidance Using Hybrid ARIMA-LSTM Models. Ocean Engineering, 2022, 256. DOI: 10.1016/j.oceaneng.2022.111527. [24] AHMED I, JUN M, DING Y.A Spatio-Temporal Track Association Algorithm Based on Marine Vessel Automatic Identification System Data. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 20783-20797. [25] LIU S Y, OUYANG Z L, CHEN G, et al. Black-Box Modeling of Ship Maneuvering Motion Based on Gaussian Process Regression with Wavelet Threshold Denoising. Ocean Engineering, 2023, 271. DOI: 10.1016/j.oceaneng.2023.113765. [26] LI H H, JIAO H, YANG Z L.AIS Data-Driven Ship Trajectory Prediction Modelling and Analysis Based on Machine Learning and Deep Learning Methods. Transportation Research(Part E: Logistics and Transportation Review), 2023, 175. DOI: 10.1016/j.tre.2023.103152. [27] ZHANG C, BERGER C.Pedestrian Behavior Prediction Using Deep Learning Methods for Urban Scenarios: A Review. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(10): 10279-10301. [28] CAPOBIANCO S, FORTI N, MILLEFIORI L M, et al. Recurrent Encoder-Decoder Networks for Vessel Trajectory Prediction with Uncertainty Estimation. IEEE Transactions on Aerospace Electro-nic Systems, 2023, 59(3): 2554-2565. [29] SINGH S K, FOWDUR J S, GAWLIKOWSKI J, et al. Leveraging Graph and Deep Learning Uncertainties to Detect Anomalous Maritime Trajectories. IEEE Transactions on Aerospace Electronic Systems, 2022, 23(12): 23488-23502. [30] LI H H, XING W B, JIAO H, et al. Deep Bi-directional Information-Empowered Ship Trajectory Prediction for Maritime Autonomous Surface Ships. Transportation Research(Part E: Logistics and Transportation Review), 2024, 181. DOI: 10.1016/j.tre.2023.103367. [31] LIU R W, HU K L, LIANG M H, et al. QSD-LSTM: Vessel Tra-jectory Prediction Using Long Short-Term Memory with Quaternion Ship Domain. Applied Ocean Research, 2023, 136. DOI: 10.1016/j.apor.2023.103592. [32] CHEN P, LIU S, LUKAČ N. CNN-Based Vessel Meeting Know-ledge Discovery from AIS Vessel Trajectories. Journal of Database Management, 2023, 34(3): 1-38. [33] JIA C F, MA J.Conditional Temporal GAN for Intent-Aware Ve-ssel Trajectory Prediction in the Precautionary Area. Engineering Applications of Artificial Intelligence, 2023, 126. DOI: 10.1016/j.engappai.2023.106776. [34] ZHANG C K, BIN J C, LIU Z.TrajBERT-DSSM: Deep Bidirectional Transformers for Vessel Trajectory Understanding and Destination Prediction. Ocean Engineering, 2024, 297. DOI: 10.1016/j.oceaneng.2024.117147. [35] WANG S W, LI Y, ZHANG Z Y, et al. Big Data Driven Vessel Trajectory Prediction Based on Sparse Multi-graph Convolutional Hybrid Network with Spatio-Temporal Awareness. Ocean Enginee-ring, 2023, 287. DOI: 10.1016/j.oceaneng.2023.115695. [36] CEN J, LI J X, LIU X, et al. A Hybrid Prediction Model of Vessel Trajectory Based on Attention Mechanism and CNN-GRU. Journal of Engineering for the Maritime Environment, 2024. DOI: 10.1177/14750902231226162. [37] LEE H, PARK D.Collision Evasive Action Timing for MASS Using CNN-LSTM-Based Ship Trajectory Prediction in Restricted Area. Ocean Engineering, 2024, 294. DOI: 10.1016/j.oceaneng.2024.116766. [38] WANG S W, LI Y, XING H, et al. Vessel Trajectory Prediction Based on Spatio-Temporal Graph Convolutional Network for Complex and Crowded Sea Areas. Ocean Engineering, 2024, 298. DOI: 10.1016/j.oceaneng.2024.117232. [39] LIU R W, ZHENG W X, LIANG M H.Spatio-Temporal Multi-graph Transformer Network for Joint Prediction of Multiple Vessel Trajectories. Engineering Applications of Artificial Intelligence, 2024, 129. DOI: 10.1016/j.engappai.2023.107625. [40] LU Y, CAO C Q, ZHANG Y F.Learnable Locality-Sensitive Ha-shing for Video Anomaly Detection. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(2): 963-976. [41] VASWANI A, SHAZEER N, PARMAR N, et al.Attention Is All You Need // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 6000-6010.
2025, Vol. 38 
