Occupancy Modeling for Rare Species Using Large Datasets: A Subsampling Approach
Bibliographic record
Abstract
ABSTRACT Citizen science monitoring programs, such as the Breeding Bird Survey, provide a wealth of data for understanding species abundance and distribution. However, traditional approaches for occupancy modeling of rare species can be difficult to apply to large, imbalanced datasets. We propose a new method for occupancy modeling where the original dataset is subsampled seasonally, keeping all sites with at least one detection along with a random sample of sites with no detections. Occupancy models cannot be fit directly to these subsampled data because the assumption of binomial sampling no longer holds. However, we show that the occupancy probability is adjusted by an offset, meaning inference on the effects of predictors is still valid. We propose a method for model fitting via direct maximum likelihood and demonstrate via simulation that this leads to computational gains. We illustrate our method using data on Canada Warblers (Cardellina canadensis) from the Breeding Bird Survey in Ontario, Canada from 1997 to 2018, where 95% of sites have zero detections annually, demonstrating that we can accurately estimate the occupancy and detection parameters, including estimating the effects of habitat covariates, using just 10% of the original dataset.
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 | 0.017 | 0.032 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".