Navigating the Annotation Bottleneck: Active Learning for Scalable Maritime Data Analytics
Bibliographic record
Abstract
The analysis of maritime vessel trajectories is critical for enhancing safety, security, and operational efficiency in global shipping. However, large-scale manual annotation of Automatic Identification System (AIS) data remains a significant bottleneck due to its labour-intensive and costly nature. This paper introduces a novel Active Learning (AL) framework for trajectory classification, designed to minimize annotation effort while maintaining high model performance. The approach leverages time-series transformer embeddings to generate compact, temporally informed representations of vessel tracks, which are clustered to enable diversity-aware sampling. Four AL strategies - random, uncertainty-based, diversity-based, and a hybrid uncertainty-diversity approach - are evaluated within a scalable pipeline that integrates a vector database for efficient retrieval and a lightweight neural network for classification. Experiments on 5,000 vessel tracks demonstrate that the hybrid strategy achieves a Macro F1-score of 0.736 and Macro Precision of 0.784, while reducing labelling requirements by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\sim 40 {\%}$</tex> compared to random sampling. Through 70 AL iterations, the hybrid sampling method balances exploration (diverse featurespace coverage) and exploitation (high-uncertainty sample selection), accelerating learning convergence. The framework's scalability is validated via integration with vector search infrastructure, enabling real-time deployment. Beyond maritime data analytics, this work generalizes to other time-series domains, such as air traffic management (ADS-B), IoT sensor streams, logistics, and Mobile Advertising Identification (MAID) data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".