A Multi-level System for Delivering Biodiversity Knowledge, Data Analysis and Pest Management Recommendations to Growers, for Environmentally Sustainable Crop Protection
Bibliographic record
Abstract
Agricultural systems in Canada are extensive in area, but not monitored or managed intensively. We developed informatics methods to better anticipate the severity, timing and geography of emerging pest risks to crops. The target insects, grasshoppers (Orthoptera: Acrididae), present special challenges in North America, as well as in China, because they occur as a complex of many species, only some of which represent significant risk to crops. We developed a Geographic Information System of insect and weather data in support of environmentally sustainable control methods. GIS-based maps of the outputs of simple weather-driven models of insect stage were provided to growers through a website containing current conditions. We combined delivery of this information with on-line training and non-technical tools for insect identification and selection of management actions. Color images for over 60 grasshopper species that assist recognition of pest versus non-pest species were provided on-line, with additional details provided in printed booklets (3500 copies were distributed free of charge). We also developed an iPhone application that provides similar information and assistance in recognizing species. We invited growers to attend on-line webinars (75 attendees) and in-person workshops (413 participants) for instruction on using the photographs and identification tips. A post-workshop survey completed by all the attendees indicated that most of the attendees (91%) scout their fields to check for the presence of grasshoppers, and that a majority of the farmers (90%) monitor or check their fields themselves, indicating that individual access to information is a valuable feature. Only 18 of the farmers at the workshops indicated that they had previously used species identification to determine pest risk status.
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 | 0.004 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.078 | 0.042 |
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".