Enhanced Use of New Seabed Mapping Technology in the Bedford Basin Through Statistical Imputation and Machine Learning
Bibliographic record
Abstract
Acoustic data collected by multibeam echosounders (MBES) are increasingly used for high resolution seabed mapping. The relationships between substrate properties and the acoustic response of the seafloor depends on the acoustic angle of incidence and the operating frequency of the sonar. These dependencies are often treated as confounding factors for seabed mapping, yet they can also provide increased information useful for discriminating benthic substrates or habitats. Using a multi-frequency case study from the Bedford Basin, Nova Scotia, machine learning methods are explored that enable increased utilization of MBES data collected at multiple frequencies over a range of incidence angles for seabed mapping. Multiple imputation is used to augment the angular multi-frequency MBES data, which enables accurately modelling distributions of substrate properties at a high spatial resolution. In addition to facilitating continuous spatial prediction, the high-resolution imputed angular models performed favourably compared to alternative approaches. Presenter Bio Originally from Massachusetts, Ben received his B/Sc/ at Acadia University, Nova Scotia, in Earth and Environmental Science, with an honours in paleolimnology. He went on to complete a Ph.D. at Memorial University of Newfoundland, in the Department of Geography, where he studied benthic habitats in coastal Arctic environments. Part of that research was on benthic habitat mapping, which has since become his primary research focus. He currently holds an OFI International Postdoc in the Department of Oceanography at Dalhousie University, Halifax, Nova Scotia, where he is working on benthic habitat mapping in the Northwest Atlantic region at fine and broad scales, including locations in the Bay of Fundy, eastern shore of Nova Scotia, and broader continental shelf.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".