Hybrid deep learning models for ship trajectory prediction in complex scenarios based on AIS data

IF 4.3 2区 工程技术 Q1 ENGINEERING, OCEAN Applied Ocean Research Pub Date : 2024-09-20 DOI:10.1016/j.apor.2024.104231
Zhiheng Liu , Wenjuan Qi , Suiping Zhou , Wenjie Zhang , Cheng Jiang , Yongshi Jie , Chengyang Li , Yuru Guo , Jianhua Guo
{"title":"Hybrid deep learning models for ship trajectory prediction in complex scenarios based on AIS data","authors":"Zhiheng Liu ,&nbsp;Wenjuan Qi ,&nbsp;Suiping Zhou ,&nbsp;Wenjie Zhang ,&nbsp;Cheng Jiang ,&nbsp;Yongshi Jie ,&nbsp;Chengyang Li ,&nbsp;Yuru Guo ,&nbsp;Jianhua Guo","doi":"10.1016/j.apor.2024.104231","DOIUrl":null,"url":null,"abstract":"<div><div>Ship trajectory prediction plays a vital role in situation awareness and maritime safety monitoring systems. Currently, the mainstream ship trajectory methods focus on single ships, and little work has been done to consider the interaction between ships. Therefore, aiming at improving the ship trajectory prediction accuracy and giving a comprehensive perspective of maritime surveillance, we proposed an integrated model with two sub-models. (1) the S-TGP model, combining Time Convolutional Network (TCN) and Gated Recurrent Unit (GRU) for single-ship trajectory with high accuracy and high generalization. The S-TGP model takes advantage of the parallel computing ability of TCN and the ability to estimate long-term correlation in the historical data. (2) the MVS-TGP model, integrating variational autoencoder (VAE) with S-TGP, for multi-ship trajectory prediction in complex scenarios. Our contributions include: (1) enhancing the accuracy of single-ship trajectory prediction with the S-TGP model; (2) improving collaborative prediction capabilities for multiple ships with the MVS-TGP model; and (3) providing real-time prediction and monitoring capabilities for maritime surveillance. Validated on AIS data from three regions, our models demonstrate superior performance and robustness compared to existing methods. The results show that the proposed models are effective in different environments and outperform the other models quantitively and qualitatively.</div></div>","PeriodicalId":8261,"journal":{"name":"Applied Ocean Research","volume":"153 ","pages":"Article 104231"},"PeriodicalIF":4.3000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Ocean Research","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0141118724003523","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, OCEAN","Score":null,"Total":0}
引用次数: 0

Abstract

Ship trajectory prediction plays a vital role in situation awareness and maritime safety monitoring systems. Currently, the mainstream ship trajectory methods focus on single ships, and little work has been done to consider the interaction between ships. Therefore, aiming at improving the ship trajectory prediction accuracy and giving a comprehensive perspective of maritime surveillance, we proposed an integrated model with two sub-models. (1) the S-TGP model, combining Time Convolutional Network (TCN) and Gated Recurrent Unit (GRU) for single-ship trajectory with high accuracy and high generalization. The S-TGP model takes advantage of the parallel computing ability of TCN and the ability to estimate long-term correlation in the historical data. (2) the MVS-TGP model, integrating variational autoencoder (VAE) with S-TGP, for multi-ship trajectory prediction in complex scenarios. Our contributions include: (1) enhancing the accuracy of single-ship trajectory prediction with the S-TGP model; (2) improving collaborative prediction capabilities for multiple ships with the MVS-TGP model; and (3) providing real-time prediction and monitoring capabilities for maritime surveillance. Validated on AIS data from three regions, our models demonstrate superior performance and robustness compared to existing methods. The results show that the proposed models are effective in different environments and outperform the other models quantitively and qualitatively.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于 AIS 数据的复杂场景下船舶轨迹预测混合深度学习模型
船舶轨迹预测在态势感知和海上安全监控系统中发挥着重要作用。目前,主流的船舶轨迹预测方法主要针对单艘船舶,很少考虑船舶之间的相互作用。因此,为了提高船舶轨迹预测的准确性,并从全面的角度看待海上监控,我们提出了一个包含两个子模型的综合模型。(1) S-TGP 模型,结合了时间卷积网络(TCN)和门控循环单元(GRU),用于高精度和高泛化的单船轨迹预测。S-TGP 模型利用了 TCN 的并行计算能力和估计历史数据中长期相关性的能力。(2) MVS-TGP 模型将变异自动编码器(VAE)与 S-TGP 相结合,用于复杂情况下的多船轨迹预测。我们的贡献包括(1) 利用 S-TGP 模型提高单船轨迹预测的准确性;(2) 利用 MVS-TGP 模型提高多船协同预测能力;以及 (3) 为海上监视提供实时预测和监控能力。通过对三个地区的 AIS 数据进行验证,与现有方法相比,我们的模型表现出更优越的性能和鲁棒性。结果表明,所提出的模型在不同环境下均有效,并在定量和定性方面优于其他模型。
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 去求助
来源期刊
Applied Ocean Research
Applied Ocean Research 地学-工程:大洋
CiteScore
8.70
自引率
7.00%
发文量
316
审稿时长
59 days
期刊介绍: The aim of Applied Ocean Research is to encourage the submission of papers that advance the state of knowledge in a range of topics relevant to ocean engineering.
期刊最新文献
Toward an AI-enhanced hydro-morphodynamic model for nature-based solutions in coastal erosion mitigation Development of Spatial Clustering Method and Probabilistic Prediction Model for Maritime Accidents Active control of vibration and radiated noise in the shaft-shell coupled system of an underwater vehicle Investigation on dynamic response of J-tube submarine cable around monopile foundation Experimental observation on violent sloshing flows inside rectangular tank with flexible baffles
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1