Flowering leafy spurge (<i>Euphorbia esula</i>) detection using unmanned aerial vehicle imagery in biological control sites: Impacts of flight height, flight time and detection method
Bibliographic record
Abstract
Abstract Leafy spurge, a noxious perennial weed, is a major threat to the prairie ecosystem in North America. Strategic planning to control leafy spurge requires monitoring its spatial distribution and spread. The ability to detect flowering leafy spurge at two biological control sites in southern Saskatchewan, Canada, was investigated using an unmanned aerial vehicle (UAV) system. Three flight missions were conducted on June 30, 2016, during the leafy spurge flowering period. Imagery was acquired at four flight heights and one or two acquisition times, depending on the site. The sites were reflown on June 28, 2017, to evaluate the change in flowering leafy spurge over time. Mixture tuned matched filtering (MTMF) and hue, intensity, and saturation (HIS) threshold analyses were used to determine flowering leafy spurge cover. Flight height of 30 m was optimal; the strongest relationships between UAV and ground estimates of leafy spurge cover (r2 = 0.76 to 0.90; normalized root mean square error [NRMSE] = 0.10 to 0.13) and stem density (r2 = 0.72 to 0.75) were observed. Detection was not significantly affected by the image analysis method (P > 0.05). Flowering leafy spurge cover estimates were similar using HIS (1.9% to 14.8%) and MTMF (2.1% to 10.3%) and agreed with the ground estimates (using HIS: r2 = 0.64 to 0.93, NRMSE = 0.08 to 0.25; using MTMF: r2 = 0.64 to 0.90, NRMSE = 0.10 to 0.27). The reduction in flowering leafy spurge cover between 2016 and 2017 detected using UAV images and HIS (8.1% at site 1 and 2.7% at site 2) was consistent with that based on ground digital photographs (10% at site 1 and 1.8% at site 2). UAV imagery is a useful tool for accurately detecting flowering leafy spurge and could be used for routine monitoring purposes in a biological control program.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".