Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA
Bibliographic record
Abstract
Dusky Grouse (Dendragapus obscurus) are an under-monitored game species in Montana and elsewhere across their distribution. Without population monitoring it is difficult to establish appropriate harvest regulations or understand the impact of environmental disturbances (e.g., timber harvest, climate change) on populations. As a first step toward developing methods for unbiased population monitoring, we must identify appropriate sampling sites, which requires knowledge of Dusky Grouse habitat. Our goal was to explore relationships between Dusky Grouse use and habitat characteristics, and then generate a state-wide map predicting Dusky Grouse habitat in Montana using two methods: resource selection functions and random forest classifiers. The Integrated Monitoring in Bird Conservation Regions program provided a multi-year dataset of Dusky Grouse observations, which we reduced to detected (n=132) and pseudo-absent (n=5960) locations, using geospatial datasets to obtain topographic and vegetation characteristics for each location. We evaluated the predictability of the two models using receiver operating characteristics and area under the curve (ROC/AUC) with k-fold cross validation and classification accuracy of an independent dataset of incidental Dusky Grouse locations. We found both models to be highly predictive and multiple habitat characteristics were found to help predict relative probability of use such as proportion of trees with a height of 16–20m and conifer forest vegetation types. We converted both models to binary values and used an ensemble (frequency histogram) approach to combine the models into a final predictive map. Consensus between the resource selection function and random forest models was high (93%) and the ensemble map had higher predictive accuracy when classifying the independent dataset than the other two models. Our results show that our ensembled model approach was able to accurately predict potential Dusky Grouse habitat and therefore can be used to delineate areas for future population monitoring of Dusky Grouse in Montana.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 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 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".