Using ecological niche models to predict the abundance and impact of invasive species: application to the common carp
Bibliographic record
Abstract
In order to efficiently manage nonindigenous species (NIS), predictive tools are needed to prioritize locations where they are likely to become established and where their impacts will be most severe. While predicting the impact of a NIS has generally proved challenging, forecasting its abundance patterns across potential recipient locations should serve as a useful surrogate method of estimating the relative severity of the impacts to be expected. Yet such approaches have rarely been applied in invasion biology. We used long-term monitoring data for lakes within the state of Minnesota and artificial neural networks to model both the occurrence as well as the abundance of a widespread aquatic NIS, common carp (Cyprinus carpio). We then tested the ability of the resulting models to (1) interpolate to new sites within our main study region, (2) extrapolate to lakes in the neighboring state of South Dakota, and (3) assessed the relative contribution of each variable to model predictions. Our models correctly identified over 83% of sites where carp are either present or absent and explained 73% of the variation in carp abundance for validation lakes in Minnesota (i.e., lakes not used to build the model). When extrapolated to South Dakota, our models correctly classified carp occurrence in 79% of lakes and explained 32% of the variation in carp abundance. Variables related to climate and water quality were found to be the most important predictors of carp distribution. These results demonstrate that ecological niche-based modeling techniques can be used to forecast both the occurrence and abundance patterns of invasive species at a regional scale. Models also yielded sensible predictions when extrapolated to neighboring regions. Such predictions, when combined, should provide more useful estimates of the overall risk posed by NIS on potential recipient systems.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 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) | 0.000 | 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 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".