Predicting multiple behaviors from GPS radiocollar cluster data
Bibliographic record
Abstract
Advancements in GPS radiotelemetry allow collection of vast data for a variety of species including those for which direct observations are typically not feasible. Predicting behavior from telemetry data is possible, but telemetry fix rate can influence inferences, and animal behavior itself can affect fix success. We use multinomial regression to predict behavior from GPS radiocollar data field validated with behavioral state information. Our study organism was a facultative carnivore, the grizzly bear (Ursus arctos) (n = 10) from a threatened population in Alberta, Canada, monitored during 2008–2010. Models using GPS cluster parameters alone successfully predicted ungulate consumption, whereas bear bedding was sufficiently identified by models that included site-level information. Predicting more complex behaviors required models incorporating both cluster parameters and habitat characteristics. No model reliably predicted vegetation feeding, probably because this activity is shorter than the time required for cluster formation. Models built using infrequent fix rates underestimated all behaviors, with bear presence at ungulate carcass sites least sensitive to fix rate variability. Behavior influenced fix success, with highest fix acquisition occurring when bears fed on vegetation. Placing predictions into a conservation context, we show that grizzly bears modify their behavior as they move through a landscape with complex human-activity patterns on reclaimed open-pit mines, foothill, and mountain regions. The modeling approach we tested needs further applications across species and ecosystems including behavioral monitoring, quantifying activity budgeting, and identifying areas/habitats important for specific behaviors that may warrant conservation.
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 | 0.003 |
| 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 | 0.000 |
| Open science | 0.001 | 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".