Predicting trajectories of coastal area vessels with a lightweight Slice-Diff self attention

Abstract Accurate prediction of vessel trajectories in coastal areas poses a significant challenge due to the large number of irregular trajectories. Existing trajectory prediction studies predominantly employ recurrent neural network (RNN) and Transformer-based methods. However, the former often en...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinxu Zhang, Jin Liu, Xiliang Zhang, Lai Wei, Zhongdai Wu, Junxiang Wang
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-01877-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850206581718777856
author Jinxu Zhang
Jin Liu
Xiliang Zhang
Lai Wei
Zhongdai Wu
Junxiang Wang
author_facet Jinxu Zhang
Jin Liu
Xiliang Zhang
Lai Wei
Zhongdai Wu
Junxiang Wang
author_sort Jinxu Zhang
collection DOAJ
description Abstract Accurate prediction of vessel trajectories in coastal areas poses a significant challenge due to the large number of irregular trajectories. Existing trajectory prediction studies predominantly employ recurrent neural network (RNN) and Transformer-based methods. However, the former often encounter challenges such as gradient vanishing or exploding, and the latter tend to focus on global temporal dependencies, making it difficult to capture local irregular trajectory features in coastal maritime areas. Recently, graph-based methods have also been used to predict trajectories, however processing graph-structured data introduces significant increase in computation. In responding to these, this paper proposes a framework based on a novel lightweight Slice-Diff self attention, which consists of several key components. Firstly, the trajectory slice difference encoder (TSDE) utilizes slice embedding (SE) to enrich the cross dimensional dependencies contained in the input sequence, and then combines Slice-Diff self attention (SDSA) and fine-grained convolution (FGC) to comprehensively capture sequence-specific positional and directional information. Additionally, an auxiliary model, stepping bidirectional long short-term memory (S-BiLSTM) is developed to capture global temporal dependencies within the whole sequence. Finally, the fine-grained trajectory features obtained from TSDE and the global temporal dependencies compensated by S-BiLSTM are combined through the fully connected layer to predict coastal vessel trajectories. Extensive experimental results on three real-world automatic identification system (AIS) datasets demonstrate the effectiveness of proposed framework against other baselines.
format Article
id doaj-art-60f5896fa2bc46f1ae4e52a6a1a3ec75
institution OA Journals
issn 2199-4536
2198-6053
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-60f5896fa2bc46f1ae4e52a6a1a3ec752025-08-20T02:10:46ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-04-0111511710.1007/s40747-025-01877-xPredicting trajectories of coastal area vessels with a lightweight Slice-Diff self attentionJinxu Zhang0Jin Liu1Xiliang Zhang2Lai Wei3Zhongdai Wu4Junxiang Wang5College of Information Engineering, Shanghai Maritime UniversityCollege of Information Engineering, Shanghai Maritime UniversityCollege of Information Engineering, Shanghai Maritime UniversityCollege of Information Engineering, Shanghai Maritime UniversityState Key Laboratory of Maritime Technology and Safety, Shanghai Ship and Shipping Research InstituteCOSCO Shipping Technology, Co., Ltd.Abstract Accurate prediction of vessel trajectories in coastal areas poses a significant challenge due to the large number of irregular trajectories. Existing trajectory prediction studies predominantly employ recurrent neural network (RNN) and Transformer-based methods. However, the former often encounter challenges such as gradient vanishing or exploding, and the latter tend to focus on global temporal dependencies, making it difficult to capture local irregular trajectory features in coastal maritime areas. Recently, graph-based methods have also been used to predict trajectories, however processing graph-structured data introduces significant increase in computation. In responding to these, this paper proposes a framework based on a novel lightweight Slice-Diff self attention, which consists of several key components. Firstly, the trajectory slice difference encoder (TSDE) utilizes slice embedding (SE) to enrich the cross dimensional dependencies contained in the input sequence, and then combines Slice-Diff self attention (SDSA) and fine-grained convolution (FGC) to comprehensively capture sequence-specific positional and directional information. Additionally, an auxiliary model, stepping bidirectional long short-term memory (S-BiLSTM) is developed to capture global temporal dependencies within the whole sequence. Finally, the fine-grained trajectory features obtained from TSDE and the global temporal dependencies compensated by S-BiLSTM are combined through the fully connected layer to predict coastal vessel trajectories. Extensive experimental results on three real-world automatic identification system (AIS) datasets demonstrate the effectiveness of proposed framework against other baselines.https://doi.org/10.1007/s40747-025-01877-xIrregular trajectory feature extractionTrajectory slice and differenceVessel trajectory predictionCoastal collision avoidanceAutomatic identification system
spellingShingle Jinxu Zhang
Jin Liu
Xiliang Zhang
Lai Wei
Zhongdai Wu
Junxiang Wang
Predicting trajectories of coastal area vessels with a lightweight Slice-Diff self attention
Complex & Intelligent Systems
Irregular trajectory feature extraction
Trajectory slice and difference
Vessel trajectory prediction
Coastal collision avoidance
Automatic identification system
title Predicting trajectories of coastal area vessels with a lightweight Slice-Diff self attention
title_full Predicting trajectories of coastal area vessels with a lightweight Slice-Diff self attention
title_fullStr Predicting trajectories of coastal area vessels with a lightweight Slice-Diff self attention
title_full_unstemmed Predicting trajectories of coastal area vessels with a lightweight Slice-Diff self attention
title_short Predicting trajectories of coastal area vessels with a lightweight Slice-Diff self attention
title_sort predicting trajectories of coastal area vessels with a lightweight slice diff self attention
topic Irregular trajectory feature extraction
Trajectory slice and difference
Vessel trajectory prediction
Coastal collision avoidance
Automatic identification system
url https://doi.org/10.1007/s40747-025-01877-x
work_keys_str_mv AT jinxuzhang predictingtrajectoriesofcoastalareavesselswithalightweightslicediffselfattention
AT jinliu predictingtrajectoriesofcoastalareavesselswithalightweightslicediffselfattention
AT xiliangzhang predictingtrajectoriesofcoastalareavesselswithalightweightslicediffselfattention
AT laiwei predictingtrajectoriesofcoastalareavesselswithalightweightslicediffselfattention
AT zhongdaiwu predictingtrajectoriesofcoastalareavesselswithalightweightslicediffselfattention
AT junxiangwang predictingtrajectoriesofcoastalareavesselswithalightweightslicediffselfattention