UAV‐based high‐throughput phenotyping for crop growth analysis and seed yield prediction in a nested association mapping population of lentils
Bibliographic record
Abstract
Abstract Unoccupied aerial vehicle (UAV)‐based high‐throughput phenotyping provides scalable and cost‐effective access to phenotypic information for crop improvement, yet its application in minor crops such as lentil ( Lens culinaris Medik.) remains limited. This study applied UAV‐derived canopy traits and crop growth regression modeling to a nested association mapping population developed from CDC Redberry crossed with 32 diverse founder lines. UAV imagery collected across four site‐years was used to capture canopy height, crop area, and crop volume per plot basis at multiple time points. Crop growth regression models were fitted to derive crop growth parameters, maximum canopy size, growth rate, and cumulative growth anchored to phenological stages. These static and time‐series traits were evaluated for seed yield prediction using partial least squares regression with a 70:20:10 data split and 10‐fold cross‐validation. Static traits such as maximum crop volume and maximum crop area were consistently associated with yield. Dynamic trait‐based models improved prediction accuracy and identified the swollen pod stage (R5–R6) as the most informative forecasting window. External validation using an independent trial confirmed the generalizability of the approach. This study presents a UAV phenotyping framework that supports crop growth dissection and early yield prediction and downstream trait discovery in lentil.
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 | 0.001 |
| 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".