Evaluation of Methods for Identification of Early Detection Monitoring Sites Based on Habitat Suitability for Invasive European Green Crab in the Salish Sea, British Columbia
Bibliographic record
Abstract
The European Green Crab (EGC) is a high-risk global invader that can devastate coastal marine ecosystems by displacing native species, degrading and disturbing native habitats (including eelgrass), and altering food webs. EGC has recently been detected in the Canadian portion of the Salish Sea. As EGC continue to establish in the region, identifying locations on which to focus limited monitoring resources is an ongoing problem given the vast amount of coastal habitat that could be occupied by the species. A variety of methods can be used to identify highly suitable habitats for EGC at a range of spatial scales. However, none have been evaluated in the context of informing EGC management, nor for the Canadian portion of the Salish Sea. Here we evaluate five individual methods developed to assess habitat suitability for EGC (i.e., MaxEnt, stochastic gradient boosted linear and logistic regression models, a rapid site selection tool, and a qualitative site assessment and ranking tool) and five derived models generated by multiplying the outputs of these individual models. Each model relied on slightly different environmental and habitat input variables affecting EGC invasion success. Thus, rather than identifying a single preferred model, we used a multi-model ensemble approach to identify sites that are expected to be most suitable for the species. The ensemble approach likely increases predictive power by including both environmental and habitat characteristics when identifying priority sites for early detection/monitoring for EGC in the Canadian waters of the Salish Sea. Finally, we describe how the models evaluated here, alone or in combination, could be used to identify additional sites either within the Salish Sea or into new areas.
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 | 0.007 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".