Deriving percent crop cover over agriculture canopies using hyperspectral remote sensing
Bibliographic record
Abstract
The objective of this study is to investigate the potential of hyperspectral remote sensing for providing green percent crop cover information over agricultural canopies for use in precision farming. Ground measurements and airborne hyperspectral Probe-1 data were acquired over two agricultural sites in July 1999 near Clinton, Ontario, Canada, and in July 2000 near Indian Head, Saskatchewan, Canada. A manual endmember selection and extraction approach was used to unmix the reflectance cubes. Linear constrained and weakly constrained unmixing was conducted to determine crop endmember fractions. Results indicate that the two spectral unmixing algorithms were equally successful. If prior knowledge of the fields exists, a manual endmember selection technique is a suitable approach for the selection of endmembers in an image scene. Correlations between ground data and Probe-1 crop fractions showed very good results (root mean square error (RMSE) of ±11.06% and ±11.20% and index of agreement (D) of 0.91 and 0.90 for constrained and weakly constrained unmixing, respectively) when the endmembers were adjusted for their impurity. This highlighted the importance of finding pure or the "purest" pixels for each endmember in the image scene. The use of spectral unmixing to quantify within-crop and within-field percent crop cover showed mixed success. Canola and wheat crops (RMSE of ±10.67% and ±11.77%; D of 0.94 and 0.85) revealed better correlations than the bean and corn crops (RMSE of ±10.83% and ±12.46%; D of 0.64 and 0.59). The somewhat poor results for pea crops (RMSE of ±9.70%; D of 0.58) are possibly due to the ground vertical photograph classification process where it was difficult to distinguish pea stems and residue components.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".