Assessing foraging landscape quality in Quebec's commercial beekeeping through remote sensing, machine learning, and survival analysis
Bibliographic record
Abstract
Honey bees (Apis mellifera) play an important role in our agricultural systems. In recent years, beekeepers have reported high colony mortality rates in several parts of the world. Inadequate foraging landscapes are often cited as a major factor deterring honey bee colony health. Few studies, if any, have yet used large-scale datasets to assess the quality of landscapes encountered in commercial pollination activities. Here, we coupled a unique dataset comprising georeferenced reports on 17,743 colonies in the province of Quebec, Canada, with data derived from satellite remote sensing, to compute landscape metrics at each visited location. We ran a Cox and a random survival forests (RSF) model with time-weighted features to predict the lifespan of colonies in various landscape scenarios. Survival estimates from our RSF model indicate that colonies foraging primarily in forested areas exhibit higher survival rates, whereas those in cranberry- and maize-dominated landscapes may face lower survival probabilities. Our findings suggest that vegetation abundance could play a significant role in shaping outcomes. Additionally, landscape diversity within a 1 km radius seems to have a positive effect, with potentially greater benefits in areas where vegetation is sparse. While topography contributes valuable predictive insights, its effects are complex and challenging to fully interpret.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 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".