Predicting the Distribution and Ecological Niche of Unexploited Snow Crab (Chionoecetes opilio) Populations in Alaskan Waters: A First Open-Access Ensemble Model
Bibliographic record
Abstract
Populations of the snow crab (Chionoecetes opilio) are widely distributed on high-latitude continental shelves of the North Pacific and North Atlantic, and represent a valuable resource in both the United States and Canada. In US waters, snow crabs are found throughout the Arctic and sub-Arctic seas surrounding Alaska, north of the Aleutian Islands, yet commercial harvest currently focuses on the more southerly population in the Bering Sea. Population dynamics are well-monitored in exploited areas, but few data exist for populations further north where climate trends in the Arctic appear to be affecting species' distributions and community structure on multiple trophic levels. Moreover, increased shipping traffic, as well as fisheries and petroleum resource development, may add additional pressures in northern portions of the range as seasonal ice cover continues to decline. In the face of these pressures, we examined the ecological niche and population distribution of snow crabs in Alaskan waters using a GIS-based spatial modeling approach. We present the first quantitative open-access model predictions of snow-crab distribution, abundance, and biomass in the Chukchi and Beaufort Seas. Multi-variate analysis of environmental drivers of species' distribution and community structure commonly rely on multiple linear regression methods. The spatial modeling approach employed here improves upon linear regression methods in allowing for exploration of nonlinear relationships and interactions between variables. Three machine-learning algorithms were used to evaluate relationships between snow-crab distribution and environmental parameters, including TreeNet, Random Forests, and MARS. An ensemble model was then generated by combining output from these three models to generate consensus predictions for presence-absence, abundance, and biomass of snow crabs. Each algorithm identified a suite of variables most important in predicting snow-crab distribution, including nutrient and chlorophyll-a concentrations in overlying waters, temperature, salinity, and annual sea-ice cover; this information may be used to develop and test hypotheses regarding the ecology of this species. This is the first such quantitative model for snow crabs, and all GIS-data layers compiled for this project are freely available from the authors, upon request, for public use and improvement.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".