Large-Scale Long-Term Prediction of Ship AIS Tracks via Linear Networks with a Look-Back Window Decomposition Scheme of Time Features
Abstract
:1. Introduction
2. Related Work
3. The Proposed Method
3.1. Definition
- is the dataset used in this experiment, which includes all the AIS ship trajectory sequences.
- refers to a segment of future time steps in a sequence, while represents a specific point within that future segment.
- represents the length of the sequence.
- represents a given historical sequence . The task of time series forecasting is to predict the values at future time steps, where t ranges from to .
- represents the number of variables contained within a time series.
- represents the output obtained after passing the input data through a single-layer network during the training process.
- represents trajectory prediction for a specific time step in the future.
- Channel refers to the different features in the input AIS data. By creating independent channels for each feature, the model can better learn and express the dynamic changes and relationships between different features, thereby improving its ability to predict, analyze, and make decisions.
- Individual means creating a separate channel for each feature so that the model can independently learn and represent each feature.
- Kernel size represents the sliding window size used in the model to decompose temporal and spatial features.
3.2. Linear Networks with Time-Feature Decomposition
3.3. Improved Linear Networks with Multiple Feature Processing Capabilities
Algorithm 1 Pseudocode of the improved multi-input multi-output linear networks with time-feature decomposition mode. |
|
3.4. AIS Data Pre-Processing
4. Experiment and Discussion
4.1. AIS Dataset
4.2. Experimental Settings
4.3. Evaluation Criteria
4.4. Experimental Results
4.5. Parameter Selection
4.6. Discussion
5. Conclusions
5.1. Limitations
5.2. Future Work
Author Contributions
Funding
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Kundakçı, B.; Nas, S.; Gucma, L. Prediction of Ship Domain on Coastal Waters by Using AIS Data. Ocean Eng. 2023, 273, 113921. [Google Scholar] [CrossRef]
- Panda, J.P. Machine Learning for Naval Architecture, Ocean and Marine Engineering. J. Mar. Sci. Technol. 2023, 28, 1–26. [Google Scholar] [CrossRef]
- Liu, T.; Ma, J. Ship Navigation Behavior Prediction Based on AIS Data. IEEE Access 2022, 10, 47997–48008. [Google Scholar] [CrossRef]
- Shi, Y.; Long, C.; Yang, X.; Deng, M. Abnormal Ship Behavior Detection Based on AIS Data. Appl. Sci. 2022, 12, 4635. [Google Scholar] [CrossRef]
- Lin, Q.; Yin, B.; Zhang, X.; Grofill, M.; Feng, H. Evaluation of Ship Collision Risk in Ships’ Routeing Waters: A Gini Coefficient Approach Using AIS Data. Phys. A Stat. Mech. Its Appl. 2023, 624, 128936. [Google Scholar] [CrossRef]
- Burnham, K.L. Information Fusion for an Unmanned Underwater Vehicle through Probabilistic Prediction and Optimal Matching. Master’s Thesis, Massachusetts Institute of Technology, Sloan School of Management, Operations Research Center, Cambridge, MA, USA, 2020. [Google Scholar]
- Keller, J. UUV Networks Needed for Covert Surveillance of Global Shipping. Mil. Aerosp. Electron. 2016, 27, 25. [Google Scholar]
- Keller, J. Navy Eyes UUV Weapons Payloads to Stop or Disable 160-Foot Ships at Sea. Mil. Aerosp. Electron. 2018, 29, 28. [Google Scholar]
- Kuznetsov, G.P.; Buldakov, I.N. UUV Launch/Recovery Moonpool Aboard Ships: Arrangement Peculiarities. Труды Крылoвскoгo Гoсударственнoгo Научнoгo Центра 2019, 389, 95–102. [Google Scholar] [CrossRef]
- Zeng, A.; Chen, M.; Zhang, L.; Xu, Q. Are Transformers Effective for Time Series Forecasting? arXiv 2022. [Google Scholar] [CrossRef]
- Oka, M.; Ma, C. Long-term Prediction for Vertical Bending Moment Utilizing the AIS Data and Global Wave Data. J. Mar. Sci. Technol. 2023, 28, 719–731. [Google Scholar] [CrossRef]
- Zhang, W. Ship Trajectory Prediction Model Based on the Longest Shared Path. Master’s Thesis, Tianjin University, Tianjin, China, 2020. [Google Scholar]
- Zhang, W.B.; Zou, Y.J.; Tang, J.J.; Ash, J.; Wang, Y.H. Short-term Prediction of Vehicle Waiting Queue at Ferry Terminal Based on Machine Learning Method. J. Mar. Sci. Technol. 2016, 21, 729–741. [Google Scholar] [CrossRef]
- Jiang, B.; Key; Zhou, W.; Chen, X. Ship Trajectory Prediction Algorithm Based on Polynomial Kalman Filter. Signal Process. 2019, 35, 741–746. [Google Scholar]
- Lei, H. Research on Port Ship Trajectory Prediction Method Based on AIS Data. Master’s Thesis, Lanzhou University, Lanzhou, China, 2021. [Google Scholar]
- Zhou, H.; Chen, Y.; Zhang, S. Ship Trajectory Prediction Based on BP Neural Network. J. Artif. Intell. 2019, 1, 29–36. [Google Scholar] [CrossRef]
- Nguyen, D.; Vadaine, R.; Hajduch, G.; Garello, R.; Fablet, R. GeoTrackNet-A Maritime Anomaly Detector Using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection. IEEE Trans. Intell. Transp. Syst. 2022, 23, 5655–5667. [Google Scholar] [CrossRef]
- Sorjamaa, A.; Hao, J.; Reyhani, N.; Ji, Y.; Lendasse, A. Methodology for Long-term Prediction of Time Series. Neurocomputing 2007, 70, 2861–2869. [Google Scholar] [CrossRef]
- Marine Cadastre. Marine Cadastre.gov. Available online: https://www.marinecadastre.gov/nationalviewer/ (accessed on 1 November 2023).
- Zhuang, C.; Chen, C. Research on Autonomous Route Generation Method Based on AIS Ship Trajectory Big Data and Improved LSTM Algorithm. Front. Neurorobot. 2022, 16, 1049343. [Google Scholar] [CrossRef]
- Nie, Y.; Nguyen, N.H.; Sinthong, P.; Kalagnanam, J. A Time Series Is Worth 64 Words: Long-Term Forecasting with Transformers. arXiv 2023. [Google Scholar] [CrossRef]
- Zaman, B.; Marijan, D.; Kholodna, T. Interpolation-Based Inference of Vessel Trajectory Waypoints from Sparse AIS Data in Maritime. J. Mar. Sci. Eng. 2023, 11, 615. [Google Scholar] [CrossRef]
- Wu, H.; Xu, J.; Wang, J.; Long, M. Autoformer: Decomposition Transformers with AutoCorrelation for Long-Term Series Forecasting. Adv. Neural Inf. Process. Syst. 2022, 34, 22419–22430. [Google Scholar]
- Zhou, H.; Zhang, S.; Peng, J.; Zhang, S.; Li, J.; Xiong, H.; Zhang, W. Informer: Beyond Efficient Transformer for Long Sequence Time-series Forecasting. arXiv 2021. [Google Scholar] [CrossRef]
- Vaswani, A.A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, A.; Polosukhin, I. Attention is All You Need. In Advances in Neural Information Processing Systems; Curran Associates, Inc.: Red Hook, NY, USA, 2017; Volume 30. [Google Scholar]
- Nguyen, D.; Fablet, R. TrAISformer-A generative transformer for AIS trajectory prediction. arXiv 2021. [Google Scholar] [CrossRef]
- Alizadeh, D.; Alesheikh, A.A.; Sharif, M. Vessel Trajectory Prediction Using Historical Automatic Identification System Data. J. Navig. 2021, 74, 156–174. [Google Scholar] [CrossRef]
- Torkington, P. Valence Force Displacement Coordinates for Systems in Which the Angles Deviate from the Ideal. J. Chem. Phys. 1950, 18, 93. [Google Scholar] [CrossRef]
- Chang, C.M.; Liou, Y.D.; Huang, Y.C.; Shen, S.E.; Yu, P.; Chuang, T.; Chiou, S.J. YOLO based deep learning on needle-type dashboard recognition for autopilot maneuvering system. Meas. Control. 2022, 55, 567–582. [Google Scholar] [CrossRef]
Parameter Name | Meaning of Parameter |
---|---|
seq_len | The length of the time series data. |
pred_len | The length of the prediction result that the model outputs. |
label_len | The length of the label data used to train or evaluate the model. |
predict_len | The length of the predicted trajectory. |
The Haversine Distance on Different Predict Lengths | Pred Length 24 | Pred Length 48 | Pred Length 96 | Pred Length 128 | Pred Length 192 | Pred Length 256 | Pred Length 300 |
---|---|---|---|---|---|---|---|
Transformer | 32.67 | 46.45 | 55.47 | 76.93 | 96.77 | 104.35 | 123.34 |
Autoformer | 23.64 | 30.93 | 56.64 | 70.31 | 83.74 | 98.34 | 103.49 |
Informer | 47.98 | 59.74 | 73.36 | 89.26 | 97.64 | 103.64 | 113.31 |
Linear | 5.34 | 13.76 | 26.49 | 30.33 | 47.36 | 52.23 | 58.64 |
NLinear | 4.30 | 4.87 | 8.68 | 13.98 | 15.27 | 23.66 | 27.87 |
PatchTST | 2.47 | 5.73 | 8.75 | 10.6 | 13.34 | 15.37 | 23.76 |
Improved DLinear | 1.26 | 3.73 | 4.23 | 7.65 | 8.98 | 10.73 | 12.23 |
The Track Deviation Angle on Different Predict Lengths | Pred Length 24 | Pred Length 48 | Pred Length 96 | Pred Length 128 | Pred Length 192 | Pred Length 256 | Pred Length 300 |
---|---|---|---|---|---|---|---|
Linear | 0.67 | 3.64 | 7.89 | 10.37 | 17.38 | 29.34 | 31.96 |
NLinear | 0.36 | 1.37 | 3.64 | 6.31 | 9.87 | 13.21 | 16.97 |
PatchTST | 1.63 | 2.31 | 6.23 | 8.69 | 12.64 | 24.56 | 46.98 |
Improved DLinear | 0.27 | 0.73 | 1.46 | 2.67 | 2.93 | 3.56 | 5.14 |
Is Individual | Loss Function | Kernel Size |
---|---|---|
True | MSE | 25 |
True | MAE | 75 |
True | MBE | 55 |
False | MSE | 75 |
False | MAE | 55 |
False | MBE | 25 |
Is Individual | Loss Function | Kernel Size | Experimental ResultHaversine Distance (m) |
---|---|---|---|
True | MSE | 25 | 11.572 |
True | MAE | 75 | 5.770 |
True | MBE | 55 | 8.653 |
False | MSE | 75 | 6.971 |
False | MAE | 55 | 7.856 |
False | MBE | 25 | 12.579 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhao, W.; Wang, D.; Gao, K.; Wu, J.; Cheng, X. Large-Scale Long-Term Prediction of Ship AIS Tracks via Linear Networks with a Look-Back Window Decomposition Scheme of Time Features. J. Mar. Sci. Eng. 2023, 11, 2132. https://doi.org/10.3390/jmse11112132
Zhao W, Wang D, Gao K, Wu J, Cheng X. Large-Scale Long-Term Prediction of Ship AIS Tracks via Linear Networks with a Look-Back Window Decomposition Scheme of Time Features. Journal of Marine Science and Engineering. 2023; 11(11):2132. https://doi.org/10.3390/jmse11112132
Chicago/Turabian StyleZhao, Wenbo, Dezhi Wang, Kai Gao, Jiani Wu, and Xinghua Cheng. 2023. "Large-Scale Long-Term Prediction of Ship AIS Tracks via Linear Networks with a Look-Back Window Decomposition Scheme of Time Features" Journal of Marine Science and Engineering 11, no. 11: 2132. https://doi.org/10.3390/jmse11112132
APA StyleZhao, W., Wang, D., Gao, K., Wu, J., & Cheng, X. (2023). Large-Scale Long-Term Prediction of Ship AIS Tracks via Linear Networks with a Look-Back Window Decomposition Scheme of Time Features. Journal of Marine Science and Engineering, 11(11), 2132. https://doi.org/10.3390/jmse11112132