Estimation of Nitrogen Content in Canola and Wheat Using Hyperspectral Drone Imaging
Bibliographic record
Abstract
Accurately estimating nitrogen (N) content in crops is essential for assessing nitrogen use efficiency (NUE), a critical parameter for optimizing fertilizer management and improving crop productivity. Traditional methods for N estimation are often destructive, time-consuming, and labor-intensive, making them impractical for large-scale applications. This study presents a non-invasive approach using unmanned aerial vehicle (UAV)-based hyperspectral imaging to estimate N content in canola and wheat at different growth stages. Hyperspectral images were collected at three growth stages during an experimental field trial conducted in Lethbridge, Alberta, Canada. Concurrently, leaf tissue samples were gathered from seven nitrogen treatment levels, each replicated four times, to serve as ground truth data. Several machine learning (ML) models were developed and evaluated to predict plant N-uptake. The results demonstrated that hyperspectral imaging could estimate N content with high accuracy. For canola, the root mean square error (RMSE) ranged from 0.51 to 0.65, with R2values between 0.73 and 0.84. For wheat, the RMSE ranged from 0.28 to 0.49, with R2values between 0.75 and 0.92. These findings highlight the potential of UAV-based hyperspectral imaging, combined with ML models, as a powerful and efficient tool for estimating N-uptake. This approach offers significant benefits for precision agriculture, enabling sustainable nitrogen management and improving crop productivity.
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".