Automated Detection of Hazardous Sea Ice Features from Upward Looking Sonar Data
Bibliographic record
Abstract
Upward-looking sonar (ULS) instruments provide extended continuous measurements of ice thicknesses and ice velocities data that are important for establishing metocean design criteria related to oil and gas operations in areas with seasonal or year-round ice cover. This paper describes the development of algorithms for the detection and measurement of hazardous ice features including: large individual ice keels with thicknesses of 5 to well over 20 m; long sections of thick hummocky (rubble) sea ice; and occurrences of multi-year ice floes. Large individual ice keels are detected using an ice draft threshold technique to identify very thick ice floes which are then categorized as to total width using a Rayleigh criteria and/or a minimum user specified threshold value (e.g. 2 m). The detection of thick hummocky ice is based on minimum criteria of ice draft data segments having median values exceeding 2.5 m and segment lengths exceeding 100 m. For qualifying segments, a selection parameter γ, defined as the 90th percentile over the 50th percentile value of ice drafts divided by the standard deviation was computed; hummocky ice is characterized by γ > 2 and is also very common for 1.5< γ <2. Results from the ongoing algorithm development for detection of multi-year ice features will also be discussed. Ice velocities can also pose difficulties for offshore oil and gas operations in terms of floating drilling platform station keeping when particularly large ice speeds occur and/or ice drift directions changing rapidly or erratically.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".