Back to search

University of British Columbia

Deep learning and information fusion for vessel destination prediction

Abstract

dc:description

Maritime shipping underpins over 80% of global trade, making accurate vessel destination prediction essential for efficient port operations, optimized resource allocation, and strategic decision-making. However, existing methods face persistent challenges, including high computational costs for trajectory comparisons and limited effectiveness and prediction stability during the early stages of a voyage, when only trajectory signals are available. This thesis addresses these gaps by developing three novel methodologies: TrajBERT Deep Semantic Similarity Model (DSSM), CrossRanker, and TrajReducer to improve prediction accuracy, robustness, and efficiency across all travel stages. Firstly, TrajBERT-DSSM is proposed to capture spatiotemporal correlations, geometric attributes, and vessel movement in trajectory comparisons. By applying geohash encoding to filter redundant trajectories and employing a contextual embedding model (TrajBERT) combined with DSSM, TrajBERT-DSSM effectively identifies destinations based on historical vessel paths. Experimental results demonstrate enhanced accuracy and stability, highlighting the benefits of integrating comprehensive trajectory features. Secondly, CrossRanker addresses the limitations of single-dimensional approaches by fusing temporal, spatial, and static signals for destination prediction. Through a two-stage ranking process, CrossRanker combines trajectory-based similarity with feature-level measurements encompassing vessel type, design characteristics, real-time draft, travel distance, and time. This cross-dimensional signal fusion enhances early-stage prediction accuracy and consistently outperforms state-of-the-art methods in terms of Top-1 accuracy and robustness metrics, thereby reducing the uncertainty inherent in partial trajectory data. Finally, TrajReducer addresses computational inefficiency in large-scale applications by clustering past trajectories based on spatial characteristics and selectively comparing them using static and dynamic vessel metadata. This approach reduces the search space for trajectory comparisons while preserving high accuracy throughout all travel stages. In evaluations, TrajReducer achieves a high reduction ratio and maintains superior accuracy even with limited trajectory signals. Overall, the proposed methods form a comprehensive framework that advances the state of the art in vessel destination prediction in terms of accuracy, efficiency, and robustness. These contributions have significant implications for the maritime industry, ranging from enhanced port scheduling and traffic management to more sustainable operational strategies, thereby supporting the growing global demand for reliable maritime logistics solutions.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy - PhD
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Electrical Engineering
Grantor dc:publisher
University of British Columbia
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhang, Chengkai
Contributors dc:contributor
  • Liu, Zheng (Professor of engineering)

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/92443

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Zhang, Chengkai. Deep learning and information fusion for vessel destination prediction. doctoral thesis, University of British Columbia, 2025. http://hdl.handle.net/2429/92443