Research on Multi-Port Ship Traffic Prediction Method Based on Spatiotemporal Graph Neural Networks

被引:10
作者
Li, Yong [1 ]
Li, Zhaoxuan [1 ]
Mei, Qiang [2 ,3 ]
Wang, Peng [2 ,4 ]
Hu, Wenlong [5 ]
Wang, Zhishan [1 ]
Xie, Wenxin [1 ]
Yang, Yang [3 ]
Chen, Yuhaoran [1 ]
机构
[1] Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
[2] Shanghai Maritime Univ, Merchant Marine Coll, Shanghai 201306, Peoples R China
[3] Jimei Univ, Nav Coll, Xiamen 361021, Peoples R China
[4] Chinese Acad Sci, Inst Comp Technol, Beijing 100086, Peoples R China
[5] Univ Auckland, Sch Comp Sci, Auckland 1010, New Zealand
基金
中国国家自然科学基金;
关键词
spatiotemporal graph neural network; traffic flow prediction; ship big data; AIS; port traffic prediction;
D O I
10.3390/jmse11071379
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
The intelligent maritime transportation system has emerged as a pivotal component in port management, owing to the rapid advancements in artificial intelligence and big data technology. Its essence lies in the application of digital modeling techniques, which leverage extensive ship data to facilitate efficient operations. In this regard, effective modeling and accurate prediction of the fluctuation patterns of ship traffic in multiple port regions will provide data support for trade analysis, port construction planning, and traffic safety management. In order to better express the potential interdependencies between ports, inspired by graph neural networks, this paper proposes a data-driven approach to construct a multi-port network and designs a spatiotemporal graph neural network model. The model incorporates graph attention networks and a dilated causal convolutional architecture to capture the temporal and spatial dimensions of traffic variation patterns. It also employs a gated-mechanism-based spatiotemporal bi-dimensional feature fusion strategy to handle the potential unequal relationships between the two dimensions of features. Compared to existing methods for port traffic prediction, this model fully considers the network characteristics of the overall port and fills the research gap in multi-port scenarios. In the experiments, real port ship traffic datasets were constructed using data from the Automatic Identification System (AIS) and port geographical information data for model validation. The results demonstrate that the model exhibits outstanding robustness and performs well in predicting traffic in multiple sub-regional port clusters.
引用
收藏
页数:18
相关论文
共 39 条
[11]   Data integrity assessment for maritime anomaly detection [J].
Iphar, Clement ;
Ray, Cyril ;
Napoli, Aldo .
EXPERT SYSTEMS WITH APPLICATIONS, 2020, 147 (147)
[12]  
Jingyuan Wang, 2021, SIGSPATIAL '21: Proceedings of the 29th International Conference on Advances in Geographic Information Systems, P145, DOI 10.1145/3474717.3483923
[13]   An Experimental Review on Deep Learning Architectures for Time Series Forecasting [J].
Lara-Benitez, Pedro ;
Carranza-Garcia, Manuel ;
Riquelme, Jose C. .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2021, 31 (03)
[14]  
Li YG, 2018, Arxiv, DOI arXiv:1707.01926
[15]   Prediction and analysis of ship traffic flow based on a space-time graph traffic computing framework [J].
Li Zhaoxuan ;
Mei Qiang ;
Li Yong ;
Wang Peng ;
Yang Yang ;
Hu Wenlong .
2022 IEEE 20TH INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING, EUC, 2022, :28-35
[16]   Fine-Grained Vessel Traffic Flow Prediction With a Spatio-Temporal Multigraph Convolutional Network [J].
Liang, Maohan ;
Liu, Ryan Wen ;
Zhan, Yang ;
Li, Huanhuan ;
Zhu, Fenghua ;
Wang, Fei-Yue .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (12) :23694-23707
[17]  
Liu RW, 2017, IEEE INT C INTELL TR
[18]   Traffic Flow Prediction With Big Data: A Deep Learning Approach [J].
Lv, Yisheng ;
Duan, Yanjie ;
Kang, Wenwen ;
Li, Zhengxi ;
Wang, Fei-Yue .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, 16 (02) :865-873
[19]  
Mohamed A, 2020, PROC CVPR IEEE, P14412, DOI 10.1109/CVPR42600.2020.01443
[20]  
Kipf TN, 2017, Arxiv, DOI arXiv:1609.02907