Species distribution models for deep-water coral habitats that account for spatial uncertainty in trap-camera fishery data
Bibliographic record
Abstract
Bottom-contact fisheries present risks to vulnerable marine ecosystems (VMEs) such as deep-water coral and sponge communities. Managing these risks requires better knowledge about VME spatial distribution within fishing areas. In this paper, we develop predictive species distribution models for alcyonacean (Order Alcyonacea) corals at SGaan Kinghlas-Bowie Seamount (SK-B) in British Columbia, Canada, based on direct presence/absence observations obtained from deep-water cameras attached to commercial fishing gear. We obtained in situ presence/absence observations of deep-water corals (Order Alcyonacea, Order Antipatharia, Order Pennatulacea, Family Stylasteridae) and sponges (Class Hexactinellida, Class Demospongiae) at 124 locations during commercial fishing trips at the SK-B marine protected area. We developed species distribution models for alcyonacean corals at SK-B and compared the performance of models using 4 different estimators of trap landing position (surface drop position and 3 Bayesian estimators) to account for spatial uncertainty in observation locations. We found that the different estimators for landing position affected variable selection, model performance, and model predictions. The best-fitting models using the 4 different landing position estimators had mean AUC values ranging from 0.71 to 0.78 and maximum kappa values ranging from 0.36 to 0.47. This study demonstrates how collaborative research surveys with commercial fisheries can provide fine-scale spatial data for coral and sponge habitat mapping using an approach that is scalable for benthic habitat risk assessment for large, possibly remote, areas where fisheries operate.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".