Lessons learned from testing the predictions of species distribution models for deep-sea corals and sponges in the Gulf of Alaska with comparisons to other Alaska ecosystems
Bibliographic record
Abstract
Abstract Species distribution models are increasingly used to inform spatial management of deep-sea coral and sponge ecosystems for guiding tools such as marine protected area placement and fisheries closures. However, species distribution models often incorporate varying data sources and methods, which need validation to test model accuracy. Existing species distribution models for the Gulf of Alaska were based on bottom trawl survey data. The objective of this study was to validate these species distribution models using independently collected underwater camera survey data collected from 2010–2022. We found that models based on bottom trawl survey data that predicted presence or absence of deep-sea corals and sponges were suitable for some taxa (fan-type corals in particular, with AUC values > 0.70), but they did not perform as well for sponges and pennatulaceans (0.60 < AUC values < 0.70). Models built on bottom trawl survey data were good at capturing absence observations, but were poor at predicting presence. These models were also poor at explaining variation in coral and sponge density, typically predicting less than 25% of the variability in observed densities. However, in most cases the density observed by underwater camera surveys was significantly correlated to density predicted by the bottom trawl survey models at the same location (p < 0.05). These results were similar to results from other model validation exercises performed in Alaska and confirm the catchability of corals and sponges is biased low in Alaska bottom trawl survey data, likely due to both the inefficiency of bottom trawls at capturing these organisms and in the difficulty in using trawls to sample in rocky, rugose and hard substrates where corals and sponges are predominantly found. The results highlight both the usefulness and limitations of these models for management, as well as the need for an iterative improvement of models incorporating better data to move forward with the management of these vulnerable marine communities.
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 | 0.026 | 0.048 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".