Early detection of clubroot in canola using drone-based hyperspectral imaging and machine learning
Bibliographic record
Abstract
Clubroot ( Plasmodiophora brassicae ) is spreading rapidly on canola ( Brassica napus ) in Canada. The disease often occurs first in small patches and then spreads across the field if not recognized and treated. Early detection is challenging because above-ground symptoms develop after the crop starts to flower, when scouting is difficult. Clubroot interferes with water uptake and delays flowering, which may result in changes in spectral reflectance that could be detected using a hyperspectral camera. The objective was to determine if a drone-mounted hyperspectral camera could be used to identify patches of clubroot from the air. Twenty-three research and commercial canola fields were imaged in Alberta and Saskatchewan during flowering from 2021 to 2023, using a remotely piloted aircraft system outfitted with a hyperspectral camera. One research site in Alberta offered an ideal mix of infected and non-infected canola for training a predictive classification model. Model development using machine learning (ML) and detailed plot mapping yielded the best results. Stochastic Gradient Boosting (SGB) consistently outperformed other ML classification algorithms tested. A 31-spectral band SGB model was subsequently used to assess 21 images from locations where comparisons with field sampling could be made with certainty. These comparisons yielded 100 % agreement in clubroot detection at the field level and > 90 % agreement for individual patches. Near infrared bands 758–764 nm were most important, especially 760 and 764 nm. Use of drones and hyperspectral technology offers promise for improved detection of clubroot so growers could choose appropriate crop rotations or treat infested patches.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 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".