Using UAVs and NDVI Readings to Predict Grower N Rates in North Carolina Cotton
Bibliographic record
Abstract
This research project was completed in conjunction with an ongoing research effort in Virginia cotton using remote sensing to predict nitrogen (N) application rates. The study was conducted in Scotland Neck, North Carolina which is in Halifax County, NC (36.1331597, -77.5026541). This area is the highest yielding county in the State of North Carolina, producing 95,000 bales in 2021 (USDA NASS, 2022). This makes it optimum for the Unmanned Aerial Vehicle (UAV) study and its algorithm creation. Through normalized difference vegetation index (NDVI) readings, the health of the plant can be determined by the foliage values presented by looking at nitrogen (N). In this study, the UAV equipped with a thermal/multispectral camera flew a 17-acre plot of upland cotton. There were two treatments during the study with the first being the grower practice of N fertilization and the second being UAV determined N application rate at five weeks after planting (5WAP) with four replications of each treatment. Each plot was twenty-four rows and spanned the length of the field. The UAV was flown at 5WAP to determine N rates at lay-by. Nitrogen was applied at a grower standard rate of 92 lbs. N/acre on four control replications and at a UAV prescription of 114 lbs. N/acre on four test replications. The study was harvested on November 8, 2022. Replication acres were counted, bale weights were taken, and lint samples were pulled at this time. The lint samples were ginned out at the Tidewater Research station in Suffolk, Virginia. The data was analyzed and found that the N prescription provided by UAV had an 83 lbs. lint/acre advantage over the grower standard. At a 42.7% turnout the grower standard N application resulted in a yield of 1,806 lbs. lint/acre and the UAV prescribed N resulted in a yield of 1,889 lbs. lint/acre.
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 | 0.001 | 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".