Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty Estimation

Vessel trajectory prediction plays a crucial role in ensuring the safety and efficiency of maritime transportation. This study proposes an innovative sequence-to-sequence model, called the Vessel Influence Long Short-Term Memory (VI-LSTM), which introduces a novel Vessel Influence Map (VIM) to quant...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyuan Guo, Huimin Qiang, Xiaodong Peng
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/2/353
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850080467243499520
author Zhiyuan Guo
Huimin Qiang
Xiaodong Peng
author_facet Zhiyuan Guo
Huimin Qiang
Xiaodong Peng
author_sort Zhiyuan Guo
collection DOAJ
description Vessel trajectory prediction plays a crucial role in ensuring the safety and efficiency of maritime transportation. This study proposes an innovative sequence-to-sequence model, called the Vessel Influence Long Short-Term Memory (VI-LSTM), which introduces a novel Vessel Influence Map (VIM) to quantitatively model the dynamic effects of surrounding vessels. To enhance reliability, VI-LSTM incorporates Gaussian distribution predictions combined with Monte Carlo dropout techniques to estimate prediction uncertainty. Additionally, a temporally weighted hybrid loss function is designed to balance prediction accuracy and uncertainty. Furthermore, this study systematically categorizes and models factors influencing vessel trajectory prediction. Experimental results demonstrate that VI-LSTM achieves a mean distance error of 330.66 m on the standard test set and 480.30 m on an unseen subject test set, outperforming other comparative models, particularly in complex navigation scenarios and high-density maritime environments. These innovations significantly improve the accuracy and generalizability of vessel trajectory predictions, leading to enhanced safety, increased efficiency, and more effective collision avoidance in maritime navigation.
format Article
id doaj-art-5efdfd0361054d5ca253ca6e74d562d8
institution DOAJ
issn 2077-1312
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-5efdfd0361054d5ca253ca6e74d562d82025-08-20T02:44:56ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-02-0113235310.3390/jmse13020353Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty EstimationZhiyuan Guo0Huimin Qiang1Xiaodong Peng2University of Chinese Academy of Sciences, Beijing 100049, ChinaUniversity of Chinese Academy of Sciences, Beijing 100049, ChinaNational Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaVessel trajectory prediction plays a crucial role in ensuring the safety and efficiency of maritime transportation. This study proposes an innovative sequence-to-sequence model, called the Vessel Influence Long Short-Term Memory (VI-LSTM), which introduces a novel Vessel Influence Map (VIM) to quantitatively model the dynamic effects of surrounding vessels. To enhance reliability, VI-LSTM incorporates Gaussian distribution predictions combined with Monte Carlo dropout techniques to estimate prediction uncertainty. Additionally, a temporally weighted hybrid loss function is designed to balance prediction accuracy and uncertainty. Furthermore, this study systematically categorizes and models factors influencing vessel trajectory prediction. Experimental results demonstrate that VI-LSTM achieves a mean distance error of 330.66 m on the standard test set and 480.30 m on an unseen subject test set, outperforming other comparative models, particularly in complex navigation scenarios and high-density maritime environments. These innovations significantly improve the accuracy and generalizability of vessel trajectory predictions, leading to enhanced safety, increased efficiency, and more effective collision avoidance in maritime navigation.https://www.mdpi.com/2077-1312/13/2/353trajectory predictionvessel influence mapuncertainty estimationmultifactor predictiontemporally weighted hybrid loss function
spellingShingle Zhiyuan Guo
Huimin Qiang
Xiaodong Peng
Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty Estimation
Journal of Marine Science and Engineering
trajectory prediction
vessel influence map
uncertainty estimation
multifactor prediction
temporally weighted hybrid loss function
title Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty Estimation
title_full Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty Estimation
title_fullStr Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty Estimation
title_full_unstemmed Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty Estimation
title_short Vessel Trajectory Prediction Using Vessel Influence Long Short-Term Memory with Uncertainty Estimation
title_sort vessel trajectory prediction using vessel influence long short term memory with uncertainty estimation
topic trajectory prediction
vessel influence map
uncertainty estimation
multifactor prediction
temporally weighted hybrid loss function
url https://www.mdpi.com/2077-1312/13/2/353
work_keys_str_mv AT zhiyuanguo vesseltrajectorypredictionusingvesselinfluencelongshorttermmemorywithuncertaintyestimation
AT huiminqiang vesseltrajectorypredictionusingvesselinfluencelongshorttermmemorywithuncertaintyestimation
AT xiaodongpeng vesseltrajectorypredictionusingvesselinfluencelongshorttermmemorywithuncertaintyestimation