Prediction of balsam fir sawfly defoliation using a Bayesian network model
Bibliographic record
Abstract
Predictions of defoliation are an important component of planning aerial insect control programs, especially for defoliators such as balsam fir sawfly ( Neodiprion abietis (Harris)) that cause severe impacts on forest growth and yield. Currently, defoliation prediction is done manually based on field observations and experience, but it is a good candidate for a Bayesian network (BN), a flexible tool for combining available expert knowledge and empirical data. We created a BN model and linked it to a geographic information system to map predicted defoliation for balsam fir sawfly in western Newfoundland over an area of 5.7 million ha from 2001 to 2008. Based on expert knowledge, probabilistic influence of egg counts, previous defoliation, and stand characteristics (species composition, stand age, and management intervention) on subsequent-year defoliation was quantified. For validation purposes, maps created using the BN model were compared with manual defoliation predictions and with measured aerial defoliation survey maps. BN model defoliation prediction maps were found to be in moderate agreement (mean Kappa value of 0.59) with conventional manual prediction maps. Overall, the BN model showed similar accuracy to manual predictions, but with benefits of automating the process and of providing more spatial detail in predictions.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".