A unified data platform for maritime analytics and predictive modeling in Arctic operations
Bibliographic record
Abstract
As the shipping industry embraces digitalization, marine operations generate vast and diverse data streams, offering significant opportunities for advanced analytics. This work presents an advanced software platform powered by a high-performance Online Analytical Processing (OLAP) database, centralizing data from multiple Canadian Coast Guard (CCG) vessels, including the Larsen, Laurier, Cygnus, Tully, and Tanu. The system integrates operational data (e.g., fuel consumption, navigation) and environmental datasets (e.g., ERA5 weather, ocean currents, ice charts) while harmonizing sensor nomenclature for consistency. For example, vessel-specific labels such as "ENG_RPM" and "ENGINE_SPEED" are standardized to a unified "Engine RPM" field using a middle vocabulary layer between database and, enabling consistent cross-vessel comparisons. The platform's visualization tool enables quality assurance (QA), exploratory data analysis (EDA), and comparative analysis across vessels using scatter plots, trajectory maps, and fuel consumption summaries. Its emissions module provides detailed hourly and trip-based emissions calculations, supporting regulatory compliance and environmental assessments. Benchmarking features include univariate and bivariate plots, time series boxplots, and heatmaps for cross-vessel comparisons under varying conditions. A key innovation is its accessible machine learning (ML) tool, allowing non-expert users to train predictive models on custom time intervals for forecasting metrics like fuel consumption, speed, and emissions. A dedicated ML Model Explainer dashboard enhances interpretability with regression statistics, feature importance rankings, and dependency charts. Additionally, the platform supports strategic planning through historical route mapping and predictive analytics, enabling users to test models under Arctic conditions. By integrating visualization, benchmarking, and ML-driven forecasting, this platform enhances maritime decision-making, optimizing operational efficiency and environmental sustainability across challenging marine environments.
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 | 0.005 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.010 | 0.008 |
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".