Predicting icebreaker resistance using machine learning and scale model testing
Bibliographic record
Abstract
Icebreakers are essential assets to enable safe Arctic and subarctic operations. These specialized ships have strengthened hulls and robust propulsion systems to enable them to manage ice and open shipping lanes through sea ice. Accurately predicting icebreaker performance is critical for designing vessels that are fit for purpose. A key factor in icebreaker performance prediction is understanding ice resistance, which determines an icebreaker’s capability to operate effectively in icy conditions. In recent years, Machine Learning (ML) methods have been increasingly utilized to predict ship efficiency, typically using parameters such as length, beam, draft, and speed. This study expands on this approach by integrating both fundamental vessel parameters and environmental factors, including ice thickness, along with detailed hull geometry data into ML models. The objective is to assess how these factors enhance the accuracy of ice resistance predictions. The dataset includes ten different icebreakers, with model tests conducted by the National Research Council of Canada’s Ocean, Coastal, and River Engineering Research Centre (NRC-OCRE). We trained boosting models to predict total ice resistance. This study demonstrates how data-driven approaches can result in novel multivariate regressions of ice resistance and highlights the improvements in prediction accuracy achieved by incorporating hull geometrical characteristics.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".