Using LSTM with Trajectory Point Correlation and Temporal Pattern Attention for Ship Trajectory Prediction
Accurate ship trajectory prediction is crucial for real-time vessel position tracking and maritime safety management. However, existing methods for ship trajectory prediction encounter significant challenges. They struggle to effectively extract long-term and complex spatial–temporal features hidden...
Gespeichert in:
Veröffentlicht in: | Electronics (Basel) 2024-12, Vol.13 (23), p.4705 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 23 |
container_start_page | 4705 |
container_title | Electronics (Basel) |
container_volume | 13 |
creator | Zhou, Yi Guo, Haitao Lu, Jun Gong, Zhihui Yu, Donghang Ding, Lei |
description | Accurate ship trajectory prediction is crucial for real-time vessel position tracking and maritime safety management. However, existing methods for ship trajectory prediction encounter significant challenges. They struggle to effectively extract long-term and complex spatial–temporal features hidden within the data. Moreover, they often overlook correlations among multivariate dynamic features such as longitude (LON), latitude (LAT), speed over ground (SOG), and course over ground (COG), which are essential for precise trajectory forecasting. To address these pressing issues and fulfill the need for more accurate and comprehensive ship trajectory prediction, we propose a novel and integrated approach. Firstly, a Trajectory Point Correlation Attention (TPCA) mechanism is devised to establish spatial connections between trajectory points, thereby uncovering the local trends of trajectory point changes. Subsequently, a Temporal Pattern Attention (TPA) mechanism is introduced to handle the associations between multiple variables across different time steps and capture the dynamic feature correlations among trajectory attributes. Finally, a Great Circle Route Loss Function (GCRLoss) is constructed, leveraging the perception of the Earth’s curvature to deepen the understanding of spatial relationships and geographic information. Experimental results demonstrate that our proposed method outperforms existing ship trajectory prediction techniques, showing enhanced reliability in multi-step predictions. |
doi_str_mv | 10.3390/electronics13234705 |
format | Article |
fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_3144068013</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A819847672</galeid><sourcerecordid>A819847672</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1921-63b8c2de98c509d433f895a00f2e7ba38000b83920dfdd07291947fefa4e466a3</originalsourceid><addsrcrecordid>eNptUU1LAzEQDaJg0f4CLwHPW_Ox3U2OpfgFFQvdnpc0H22WbbImKdJ_b2o9KDhzeMPMe28GBoA7jCaUcvSgey1T8M7KiCmhZY2mF2BEUM0LTji5_FVfg3GMHcrBMWUUjUC3jtZt4WLVvMFPm3awCaLLfj4c4dJbl-Dch6B7kax3UDgFG70ffBA9XIqUdHBwlsF9j40PcLWzwx-ToJWVp_EtuDKij3r8gzdg_fTYzF-Kxfvz63y2KCTmBBcV3TBJlOZMThFXJaWG8alAyBBdbwRl-foNo5wgZZRCNeGYl7XRRpS6rCpBb8D92XcI_uOgY2o7fwgur2wpLktUMYRpZk3OrK3odWud8SkImVPpvZXeaWNzf8YwZ2Vd1SQL6Fkgg48xaNMOwe5FOLYYtadHtP88gn4BQRt-_Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3144068013</pqid></control><display><type>article</type><title>Using LSTM with Trajectory Point Correlation and Temporal Pattern Attention for Ship Trajectory Prediction</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Zhou, Yi ; Guo, Haitao ; Lu, Jun ; Gong, Zhihui ; Yu, Donghang ; Ding, Lei</creator><creatorcontrib>Zhou, Yi ; Guo, Haitao ; Lu, Jun ; Gong, Zhihui ; Yu, Donghang ; Ding, Lei</creatorcontrib><description>Accurate ship trajectory prediction is crucial for real-time vessel position tracking and maritime safety management. However, existing methods for ship trajectory prediction encounter significant challenges. They struggle to effectively extract long-term and complex spatial–temporal features hidden within the data. Moreover, they often overlook correlations among multivariate dynamic features such as longitude (LON), latitude (LAT), speed over ground (SOG), and course over ground (COG), which are essential for precise trajectory forecasting. To address these pressing issues and fulfill the need for more accurate and comprehensive ship trajectory prediction, we propose a novel and integrated approach. Firstly, a Trajectory Point Correlation Attention (TPCA) mechanism is devised to establish spatial connections between trajectory points, thereby uncovering the local trends of trajectory point changes. Subsequently, a Temporal Pattern Attention (TPA) mechanism is introduced to handle the associations between multiple variables across different time steps and capture the dynamic feature correlations among trajectory attributes. Finally, a Great Circle Route Loss Function (GCRLoss) is constructed, leveraging the perception of the Earth’s curvature to deepen the understanding of spatial relationships and geographic information. Experimental results demonstrate that our proposed method outperforms existing ship trajectory prediction techniques, showing enhanced reliability in multi-step predictions.</description><identifier>ISSN: 2079-9292</identifier><identifier>EISSN: 2079-9292</identifier><identifier>DOI: 10.3390/electronics13234705</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Algorithms ; Correlation ; Deep learning ; Great circles ; Kalman filters ; Machine learning ; Methods ; Multivariate analysis ; Neural networks ; Real time ; Safety management ; Ship accidents & safety ; Trends</subject><ispartof>Electronics (Basel), 2024-12, Vol.13 (23), p.4705</ispartof><rights>COPYRIGHT 2024 MDPI AG</rights><rights>2024 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/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c1921-63b8c2de98c509d433f895a00f2e7ba38000b83920dfdd07291947fefa4e466a3</cites><orcidid>0000-0002-5858-7671 ; 0000-0003-0653-8373</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27922,27923</link.rule.ids></links><search><creatorcontrib>Zhou, Yi</creatorcontrib><creatorcontrib>Guo, Haitao</creatorcontrib><creatorcontrib>Lu, Jun</creatorcontrib><creatorcontrib>Gong, Zhihui</creatorcontrib><creatorcontrib>Yu, Donghang</creatorcontrib><creatorcontrib>Ding, Lei</creatorcontrib><title>Using LSTM with Trajectory Point Correlation and Temporal Pattern Attention for Ship Trajectory Prediction</title><title>Electronics (Basel)</title><description>Accurate ship trajectory prediction is crucial for real-time vessel position tracking and maritime safety management. However, existing methods for ship trajectory prediction encounter significant challenges. They struggle to effectively extract long-term and complex spatial–temporal features hidden within the data. Moreover, they often overlook correlations among multivariate dynamic features such as longitude (LON), latitude (LAT), speed over ground (SOG), and course over ground (COG), which are essential for precise trajectory forecasting. To address these pressing issues and fulfill the need for more accurate and comprehensive ship trajectory prediction, we propose a novel and integrated approach. Firstly, a Trajectory Point Correlation Attention (TPCA) mechanism is devised to establish spatial connections between trajectory points, thereby uncovering the local trends of trajectory point changes. Subsequently, a Temporal Pattern Attention (TPA) mechanism is introduced to handle the associations between multiple variables across different time steps and capture the dynamic feature correlations among trajectory attributes. Finally, a Great Circle Route Loss Function (GCRLoss) is constructed, leveraging the perception of the Earth’s curvature to deepen the understanding of spatial relationships and geographic information. Experimental results demonstrate that our proposed method outperforms existing ship trajectory prediction techniques, showing enhanced reliability in multi-step predictions.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Correlation</subject><subject>Deep learning</subject><subject>Great circles</subject><subject>Kalman filters</subject><subject>Machine learning</subject><subject>Methods</subject><subject>Multivariate analysis</subject><subject>Neural networks</subject><subject>Real time</subject><subject>Safety management</subject><subject>Ship accidents & safety</subject><subject>Trends</subject><issn>2079-9292</issn><issn>2079-9292</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNptUU1LAzEQDaJg0f4CLwHPW_Ox3U2OpfgFFQvdnpc0H22WbbImKdJ_b2o9KDhzeMPMe28GBoA7jCaUcvSgey1T8M7KiCmhZY2mF2BEUM0LTji5_FVfg3GMHcrBMWUUjUC3jtZt4WLVvMFPm3awCaLLfj4c4dJbl-Dch6B7kax3UDgFG70ffBA9XIqUdHBwlsF9j40PcLWzwx-ToJWVp_EtuDKij3r8gzdg_fTYzF-Kxfvz63y2KCTmBBcV3TBJlOZMThFXJaWG8alAyBBdbwRl-foNo5wgZZRCNeGYl7XRRpS6rCpBb8D92XcI_uOgY2o7fwgur2wpLktUMYRpZk3OrK3odWud8SkImVPpvZXeaWNzf8YwZ2Vd1SQL6Fkgg48xaNMOwe5FOLYYtadHtP88gn4BQRt-_Q</recordid><startdate>20241201</startdate><enddate>20241201</enddate><creator>Zhou, Yi</creator><creator>Guo, Haitao</creator><creator>Lu, Jun</creator><creator>Gong, Zhihui</creator><creator>Yu, Donghang</creator><creator>Ding, Lei</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L7M</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0002-5858-7671</orcidid><orcidid>https://orcid.org/0000-0003-0653-8373</orcidid></search><sort><creationdate>20241201</creationdate><title>Using LSTM with Trajectory Point Correlation and Temporal Pattern Attention for Ship Trajectory Prediction</title><author>Zhou, Yi ; Guo, Haitao ; Lu, Jun ; Gong, Zhihui ; Yu, Donghang ; Ding, Lei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1921-63b8c2de98c509d433f895a00f2e7ba38000b83920dfdd07291947fefa4e466a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Correlation</topic><topic>Deep learning</topic><topic>Great circles</topic><topic>Kalman filters</topic><topic>Machine learning</topic><topic>Methods</topic><topic>Multivariate analysis</topic><topic>Neural networks</topic><topic>Real time</topic><topic>Safety management</topic><topic>Ship accidents & safety</topic><topic>Trends</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhou, Yi</creatorcontrib><creatorcontrib>Guo, Haitao</creatorcontrib><creatorcontrib>Lu, Jun</creatorcontrib><creatorcontrib>Gong, Zhihui</creatorcontrib><creatorcontrib>Yu, Donghang</creatorcontrib><creatorcontrib>Ding, Lei</creatorcontrib><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Electronics (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhou, Yi</au><au>Guo, Haitao</au><au>Lu, Jun</au><au>Gong, Zhihui</au><au>Yu, Donghang</au><au>Ding, Lei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Using LSTM with Trajectory Point Correlation and Temporal Pattern Attention for Ship Trajectory Prediction</atitle><jtitle>Electronics (Basel)</jtitle><date>2024-12-01</date><risdate>2024</risdate><volume>13</volume><issue>23</issue><spage>4705</spage><pages>4705-</pages><issn>2079-9292</issn><eissn>2079-9292</eissn><abstract>Accurate ship trajectory prediction is crucial for real-time vessel position tracking and maritime safety management. However, existing methods for ship trajectory prediction encounter significant challenges. They struggle to effectively extract long-term and complex spatial–temporal features hidden within the data. Moreover, they often overlook correlations among multivariate dynamic features such as longitude (LON), latitude (LAT), speed over ground (SOG), and course over ground (COG), which are essential for precise trajectory forecasting. To address these pressing issues and fulfill the need for more accurate and comprehensive ship trajectory prediction, we propose a novel and integrated approach. Firstly, a Trajectory Point Correlation Attention (TPCA) mechanism is devised to establish spatial connections between trajectory points, thereby uncovering the local trends of trajectory point changes. Subsequently, a Temporal Pattern Attention (TPA) mechanism is introduced to handle the associations between multiple variables across different time steps and capture the dynamic feature correlations among trajectory attributes. Finally, a Great Circle Route Loss Function (GCRLoss) is constructed, leveraging the perception of the Earth’s curvature to deepen the understanding of spatial relationships and geographic information. Experimental results demonstrate that our proposed method outperforms existing ship trajectory prediction techniques, showing enhanced reliability in multi-step predictions.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/electronics13234705</doi><orcidid>https://orcid.org/0000-0002-5858-7671</orcidid><orcidid>https://orcid.org/0000-0003-0653-8373</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2079-9292 |
ispartof | Electronics (Basel), 2024-12, Vol.13 (23), p.4705 |
issn | 2079-9292 2079-9292 |
language | eng |
recordid | cdi_proquest_journals_3144068013 |
source | MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals |
subjects | Accuracy Algorithms Correlation Deep learning Great circles Kalman filters Machine learning Methods Multivariate analysis Neural networks Real time Safety management Ship accidents & safety Trends |
title | Using LSTM with Trajectory Point Correlation and Temporal Pattern Attention for Ship Trajectory Prediction |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T06%3A48%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Using%20LSTM%20with%20Trajectory%20Point%20Correlation%20and%20Temporal%20Pattern%20Attention%20for%20Ship%20Trajectory%20Prediction&rft.jtitle=Electronics%20(Basel)&rft.au=Zhou,%20Yi&rft.date=2024-12-01&rft.volume=13&rft.issue=23&rft.spage=4705&rft.pages=4705-&rft.issn=2079-9292&rft.eissn=2079-9292&rft_id=info:doi/10.3390/electronics13234705&rft_dat=%3Cgale_proqu%3EA819847672%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3144068013&rft_id=info:pmid/&rft_galeid=A819847672&rfr_iscdi=true |