Habitat Suitability in the Eyes of the Beholder: Using Random Forest Models to Predict Land Cover Type and Scale of Selection Through Avian Functional Traits
Bibliographic record
Abstract
Ecologists have long sought to identify the scales at which avian species select habitats from their surroundings. However, this is a challenging undertaking given the complex hierarchical nature of the processes involved in avian habitat selection and also given the selection of data scales (resolution and extents) available in satellite-derived land cover. Past research has largely neglected to consider how grain size limitations are related to species’ functional traits. Fortunately, with the increased ubiquity of available land cover maps and open-access datasets detailing avian functional traits, tackling these questions is becoming more feasible. Using data from the Ontario Land Cover Compilation v2, the Ontario Breeding Bird Atlas (2001–2005), and functional trait data from the AVONET dataset, we trained Random Forest models to predict scale-dependent land cover preferences based on avian functional traits. To capture changing scales, we used increasing pixel sizes from the land cover map of our study area which sought to replicate the different perceptual ranges of avian species. Our Random Forest models showcase the ability to accurately predict between natural and human-modified land cover with varying predictive accuracies. Notably, we observed heightened accuracy at smaller pixel sizes, with a subtle decline as grain size increased. By revealing the relationship between avian traits and habitat selection across multiple scales, our study advances our understanding of species–environment interactions, offering valuable insights for conservation strategies and a deeper understanding of avian habitat selection.
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 | 0.000 |
| 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 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".