Agent-based Modelling and Big Data: Applications for Maritime Traffic Analysis
Bibliographic record
Abstract
Agent based modeling (ABM) is a powerful tool for examining complex systems in many scientific applications, including maritime transport systems. Growing demands for freight transport and increased industry emphasis on reducing environmental impacts have heightened the focus on vessel and port efficiency. This research aimed to create a maritime route planning model to simulate vessel movement in all waterways. The goal of the ship routing model developed in this research was to develop a simulation tool capable of reproducing real world shipping routes useful for navigation planning, with emphasis on port scheduling and potential application for further use and exploration. A modified breadth-first search algorithm was implemented as a NetLogo ABM in this research. With increasing volumes of ship location monitoring data, new approaches are now possible for examining performance-based metrics and to improve simulations with more precise verification and analysis. A Satellite Automatic Identification System dataset with over 500,000 vessel logs travelling across the Pacific Ocean and into the Port of Metro Vancouver was used as the focal area for model development and validation in this study. Automatic identification system (AIS) is the global standard for maritime navigation and traffic management, and data derived from AIS messages can be used for calibrating simulation model scenarios. In this analysis, the results examined how changes in simulation parameters alter route choice behaviour and how effective large AIS datasets are for validating and calibrating model results. Using large AIS datasets, model results can be quantified to examine how closely they resemble real-time vessels in the same region. Heatmaps provide a data visualization tool that effectively uses large data sets and calculates how closely model results resemble AIS data from the same region. In the case of PMV, the Maritime Ship Routing Model (MSRM) was able to replicate path likeness with a high level of accuracy, generating realistic navigation paths between the many islands on the eastern side of southern Vancouver Island, B.C., a busy marine traffic region and sensitive ecological area. This research highlights the use of ABM as a powerful, user-friendly tool for developing maritime shipping models useful for port scheduling and route analysis. The results of this study emphasize the use of large data sets that are applicable, clean, and reliable as a crucial source for validating and calibrating the MSRM.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.015 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".