Ensemble modelling the distribution and habitat suitability of wild goat <i>Capra aegagrus</i> in southwestern Iran
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Increasing anthropogenic pressures have caused drastic population decline of wild goats Capra aegagrus. The study aim was to determine habitat suitability and explore the factors influencing habitat selection and dispersal of wild goats in the Khaeiz and Sorkh protected area, southwestern Iran. We utilized ensemble modelling based on 25 replications of 10 species distribution models GLM (generalized linear model), GAM (generalized additive model), GBM (gradient boosting model), CTA (classification tree analysis), FDA (flexible discriminant analysis), ANN (artificial neural network), MARS (multivariate adaptive regression spline), RF (random forest), MaxEnt (maximum entropy), SRE (surface range envelope). Wild goat occurrence data were collected from 2019 to 2020 and related to five variables: predator distribution, slope, distance from road, distance from water resources, and normalized difference vegetation index (NDVI). We found that distribution of predators, slope, distance from water resources and distance from roads were the most important predictors of potential habitats for wild goats. The least important variable was NDVI. Probabilistic predictions suggest that only 5.89% of the area was highly suitable habitat, whereas 46.24% was unsuitable. Ensembling individually classified presence/absence maps further indicates that 79.72% of the study area was certainly unsuitable while only 8.06% was certainly suitable for wild goats. The results can help wildlife managers and policymakers work towards conservation and management goals and decreasing the conflicts between wildlife and humans.
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.
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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 it