VISTA: Knowledge-Driven Interpretable Vessel Trajectory Imputation via Large Language Models

• URL: http://arxiv.org/abs/2601.06940v1
• Date: Sun, 11 Jan 2026 15:02:28 GMT
• Title: VISTA: Knowledge-Driven Interpretable Vessel Trajectory Imputation via Large Language Models
• Authors: Hengyu Liu, Tianyi Li, Haoyu Wang, Kristian Torp, Tiancheng Zhang, Yushuai Li, Christian S. Jensen,
• Abstract summary: Existing imputation methods emphasize trajectory recovery, paying limited attention to interpretability.<n>We propose knowledge-driven interpretable vessel trajectory imputation (VISTA)<n>VISTA offers interpretability while simultaneously providing underlying knowledge to support downstream analysis.
• Score: 17.761349370700007
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Automatic Identification System provides critical information for maritime navigation and safety, yet its trajectories are often incomplete due to signal loss or deliberate tampering. Existing imputation methods emphasize trajectory recovery, paying limited attention to interpretability and failing to provide underlying knowledge that benefits downstream tasks such as anomaly detection and route planning. We propose knowledge-driven interpretable vessel trajectory imputation (VISTA), the first trajectory imputation framework that offers interpretability while simultaneously providing underlying knowledge to support downstream analysis. Specifically, we first define underlying knowledge as a combination of Structured Data-derived Knowledge (SDK) distilled from AIS data and Implicit LLM Knowledge acquired from large-scale Internet corpora. Second, to manage and leverage the SDK effectively at scale, we develop a data-knowledge-data loop that employs a Structured Data-derived Knowledge Graph for SDK extraction and knowledge-driven trajectory imputation. Third, to efficiently process large-scale AIS data, we introduce a workflow management layer that coordinates the end-to-end pipeline, enabling parallel knowledge extraction and trajectory imputation with anomaly handling and redundancy elimination. Experiments on two large AIS datasets show that VISTA is capable of state-of-the-art imputation accuracy and computational efficiency, improving over state-of-the-art baselines by 5%-94% and reducing time cost by 51%-93%, while producing interpretable knowledge cues that benefit downstream tasks. The source code and implementation details of VISTA are publicly available.

Related papers

• CLEAR: A Knowledge-Centric Vessel Trajectory Analysis Platform [18.939378377355396]
  We present CLEAR, a knowledge-centric vessel trajectory analysis platform.<n> CLEAR transforms raw AIS data into complete, interpretable, and easily explorable vessel trajectories.<n>As part of the demo, participants can configure parameters to automatically download and process AIS data.
  arXiv  Detail & Related papers  (2026-02-09T10:32:26Z)
• Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG [51.120170062795566]
  We propose Divide-Then-Align (DTA) to endow RAG systems with the ability to respond with "I don't know" when the query is out of the knowledge boundary.<n>DTA balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.
  arXiv  Detail & Related papers  (2025-05-27T08:21:21Z)
• Damage Assessment after Natural Disasters with UAVs: Semantic Feature Extraction using Deep Learning [31.376336808244286]
  This paper proposes a novel semantic extractor that can be adopted into any machine learning downstream task.<n>The semantic extractor can be executed onboard which results in a reduction of data that needs to be transmitted to ground stations.<n>Our experimental results demonstrate the proposed method maintains high accuracy across different downstream tasks while significantly reducing the volume of transmitted data.
  arXiv  Detail & Related papers  (2024-12-14T08:56:22Z)
• KBAlign: Efficient Self Adaptation on Specific Knowledge Bases [73.34893326181046]
  We present KBAlign, a self-supervised framework that enhances RAG systems through efficient model adaptation.<n>Our key insight is to leverage the model's intrinsic capabilities for knowledge alignment through two innovative mechanisms.<n> Experiments demonstrate that KBAlign can achieve 90% of the performance gain obtained through GPT-4-supervised adaptation.
  arXiv  Detail & Related papers  (2024-11-22T08:21:03Z)
• Deep Learning for Trajectory Data Management and Mining: A Survey and Beyond [58.63558696061679]
  Trajectory computing is crucial in various practical applications such as location services, urban traffic, and public safety. We present a review of development and recent advances in deep learning for trajectory computing (DL4Traj) Notably, we encapsulate recent advancements in Large Language Models (LLMs) that hold potential to augment trajectory computing.
  arXiv  Detail & Related papers  (2024-03-21T05:57:27Z)
• A Maritime Industry Experience for Vessel Operational Anomaly Detection: Utilizing Deep Learning Augmented with Lightweight Interpretable Models [0.19116784879310028]
  This study showcases a vessel operational anomaly detection approach that utilizes semi-supervised deep learning models augmented with lightweight interpretable surrogate models.<n>We leverage standard and Long Short-Term Memory (LSTM) autoencoders trained on normal operational data and tested with real anomaly-revealing data.
  arXiv  Detail & Related papers  (2023-12-30T01:31:54Z)
• Evaluating the structure of cognitive tasks with transfer learning [67.22168759751541]
  This study investigates the transferability of deep learning representations between different EEG decoding tasks. We conduct extensive experiments using state-of-the-art decoding models on two recently released EEG datasets.
  arXiv  Detail & Related papers  (2023-07-28T14:51:09Z)
• Efficient Visual Fault Detection for Freight Train Braking System via Heterogeneous Self Distillation in the Wild [8.062167870951706]
  This paper proposes a heterogeneous self-distillation framework to ensure detection accuracy and speed. We employ a novel loss function that makes the network easily concentrate on values near the label to improve learning efficiency. Our framework can achieve over 37 frames per second and maintain the highest accuracy in comparison with traditional distillation approaches.
  arXiv  Detail & Related papers  (2023-07-03T01:27:39Z)
• A Dimensional Structure based Knowledge Distillation Method for Cross-Modal Learning [15.544134849816528]
  We discover the correlation between feature discriminability and dimensional structure (DS) by analyzing and observing features extracted from simple and hard tasks. We propose a novel cross-modal knowledge distillation (CMKD) method for better supervised cross-modal learning (CML) performance. The proposed method enforces output features to be channel-wise independent and intermediate ones to be uniformly distributed, thereby learning semantically irrelevant features from the hard task to boost its accuracy.
  arXiv  Detail & Related papers  (2023-06-28T07:29:26Z)
• Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction [80.64518530825801]
  We develop a Gradient Reinforcement Learning (GIRL) method to encourage pseudo-labeled data to imitate the gradient descent direction on labeled data. We also leverage GIRL to solve all IE sub-tasks (named entity recognition, relation extraction, and event extraction) in low-resource settings.
  arXiv  Detail & Related papers  (2022-11-11T05:37:19Z)
• Segmentation-guided Domain Adaptation for Efficient Depth Completion [3.441021278275805]
  We propose an efficient depth completion model based on a vgg05-like CNN architecture and a semi-supervised domain adaptation approach. In order to boost spatial coherence, we guide the learning process using segmentations as additional source of information. Our approach improves on previous efficient and low parameter state of the art approaches while having a noticeably lower computational footprint.
  arXiv  Detail & Related papers  (2022-10-14T13:01:25Z)
• Learning with Recoverable Forgetting [77.56338597012927]
  Learning wIth Recoverable Forgetting explicitly handles the task- or sample-specific knowledge removal and recovery. Specifically, LIRF brings in two innovative schemes, namely knowledge deposit and withdrawal. We conduct experiments on several datasets, and demonstrate that the proposed LIRF strategy yields encouraging results with gratifying generalization capability.
  arXiv  Detail & Related papers  (2022-07-17T16:42:31Z)
• Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability [53.27240222619834]
  Knowledge Distillation as Efficient Pre-training aims to efficiently transfer the learned feature representation from pre-trained models to new student models for future downstream tasks. Our method performs comparably with supervised pre-training counterparts in 3 downstream tasks and 9 downstream datasets requiring 10x less data and 5x less pre-training time.
  arXiv  Detail & Related papers  (2022-03-10T06:23:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.