WEED COVER ON AND BETWEEN CORN ROWS IMPLICATIONS FOR REAL-TIME WEED DETECTION
Bibliographic record
Abstract
The spatial distribution of weeds in crop fields is heterogeneous. Therefore, limiting herbicides application to weed infested areas would lead to economical and environmental benefits. For real-time spot treatments, sensors detecting weed patches are needed. Vegetation sensors could be used in the inter-rows to trigger herbicide spraying on both rows and inter-rows if weed cover on and between the crop rows is uniform. To verify this hypothesis, weed cover on and between corn rows was evaluated using photographs acquired in corn fields at the 3 to 5 leaf stage. A one hectare plot was sampled in 2004, 2005 and 2007 at one location and nine one hectare plots were sampled in corn fields dispersed across the province of Quebec (Canada) in 2008. All fields were planted in corn under conventional tillage (75 cm row spacing). A segmentation algorithm was used to isolate vegetation pixels. Samples for the analysis consisted of 23 x 750 mm strips free of corn plants and covering three regions: undisturbed inter-row (UIR), corn row and inter-row compacted by tractor and/or seeders wheel during the seeding process (WIR). Repeated Anova measures indicated that weed cover on the undisturbed inter-row was generally lower than on the CR or WIR (p<0.001). No significant difference in weed cover was observed between CR and WIR. A presence/absence contingency table showed that 13-15% of samples had no weed pixels on the WIR while pixels were present on the row, indicating that 13-15% of weeds located on the CR would be missed if detection was based on the WIR.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".