GL-LoiterDNet: A Hybrid Model for Ship Trajectory Prediction in Loitering Activity Scenarios

IF 1.8 4区 工程技术 Q2 ENGINEERING, CIVIL
Liang Huang, Peng Zou, Yuanqiao Wen, Tengda Sun, Yamin Huang, He Lin
{"title":"GL-LoiterDNet: A Hybrid Model for Ship Trajectory Prediction in Loitering Activity Scenarios","authors":"Liang Huang,&nbsp;Peng Zou,&nbsp;Yuanqiao Wen,&nbsp;Tengda Sun,&nbsp;Yamin Huang,&nbsp;He Lin","doi":"10.1155/atr/5582889","DOIUrl":null,"url":null,"abstract":"<p>In loitering activity scenarios, vessels frequently execute course changes within localized maritime spaces, often exhibiting extreme turning maneuvers that generate ultralong, dense, and highly nonlinear spatiotemporal trajectories. Traditional prediction models demonstrate limitations in processing dynamically changing trajectory features, leading to insufficient prediction accuracy under such loitering conditions. To address this challenge, this study proposes a GL-LoiterDNet, a hybrid deep learning–based vessel trajectory prediction model. The model incorporates multidimensional trajectory characterization features including speed fluctuations, navigational positions, and course differentials. It integrates 1D convolutional neural networks (1D-CNN), bidirectional gated recurrent units (BiGRU), and bidirectional long short-term memory (BiLSTM) networks to capture both localized abrupt variations and long-term evolutionary patterns in loitering trajectories, thereby mitigating feature degradation phenomena. Experimental validation using trajectory data from vessels in Sagami Bay, Japan, demonstrates that the GL-LoiterDNet model outperforms 14 baseline models in prediction accuracy and robustness. The model exhibits rolling multistep trajectory prediction capability for loitering scenarios, achieving an average positioning error below 0.7 km within 10-min prediction windows. This research can provide reliable theoretical and data-driven support for continuous vessel positioning and monitoring in complex maritime operation scenarios.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2025 1","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/5582889","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Advanced Transportation","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1155/atr/5582889","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0

Abstract

In loitering activity scenarios, vessels frequently execute course changes within localized maritime spaces, often exhibiting extreme turning maneuvers that generate ultralong, dense, and highly nonlinear spatiotemporal trajectories. Traditional prediction models demonstrate limitations in processing dynamically changing trajectory features, leading to insufficient prediction accuracy under such loitering conditions. To address this challenge, this study proposes a GL-LoiterDNet, a hybrid deep learning–based vessel trajectory prediction model. The model incorporates multidimensional trajectory characterization features including speed fluctuations, navigational positions, and course differentials. It integrates 1D convolutional neural networks (1D-CNN), bidirectional gated recurrent units (BiGRU), and bidirectional long short-term memory (BiLSTM) networks to capture both localized abrupt variations and long-term evolutionary patterns in loitering trajectories, thereby mitigating feature degradation phenomena. Experimental validation using trajectory data from vessels in Sagami Bay, Japan, demonstrates that the GL-LoiterDNet model outperforms 14 baseline models in prediction accuracy and robustness. The model exhibits rolling multistep trajectory prediction capability for loitering scenarios, achieving an average positioning error below 0.7 km within 10-min prediction windows. This research can provide reliable theoretical and data-driven support for continuous vessel positioning and monitoring in complex maritime operation scenarios.

Abstract Image

GL-LoiterDNet:一种用于船舶航迹预测的混合模型
在巡航活动场景中,船舶经常在局部海域内执行航向改变,经常表现出极端的转向机动,产生超长、密集和高度非线性的时空轨迹。传统的预测模型在处理动态变化的轨迹特征方面存在局限性,导致在这种漂移条件下预测精度不足。为了应对这一挑战,本研究提出了GL-LoiterDNet,这是一种基于深度学习的混合船舶轨迹预测模型。该模型结合了多维轨迹表征特征,包括速度波动、导航位置和航向差异。它集成了一维卷积神经网络(1D- cnn)、双向门控循环单元(BiGRU)和双向长短期记忆(BiLSTM)网络,以捕获游荡轨迹中的局部突变和长期进化模式,从而减轻特征退化现象。利用日本Sagami湾船只的轨迹数据进行的实验验证表明,GL-LoiterDNet模型在预测精度和稳健性方面优于14个基线模型。该模型对漫游场景具有滚动多步轨迹预测能力,在10 min预测窗口内平均定位误差小于0.7 km。该研究可为复杂海上作业场景下船舶连续定位与监测提供可靠的理论支持和数据驱动支持。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Advanced Transportation
Journal of Advanced Transportation 工程技术-工程:土木
CiteScore
5.00
自引率
8.70%
发文量
466
审稿时长
7.3 months
期刊介绍: The Journal of Advanced Transportation (JAT) is a fully peer reviewed international journal in transportation research areas related to public transit, road traffic, transport networks and air transport. It publishes theoretical and innovative papers on analysis, design, operations, optimization and planning of multi-modal transport networks, transit & traffic systems, transport technology and traffic safety. Urban rail and bus systems, Pedestrian studies, traffic flow theory and control, Intelligent Transport Systems (ITS) and automated and/or connected vehicles are some topics of interest. Highway engineering, railway engineering and logistics do not fall within the aims and scope of JAT.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信