Multispectral indices and advanced classification techniques to detect percent residue cover over agricultural crops using Landsat data
Bibliographic record
Abstract
Detecting and quantifying crop residue cover on agricultural fields is essential in identifying conservation tillage practices and estimating carbon sequestration, both of which are important goals within the Agricultural Policy Framework of Agriculture and Agri-Food Canada. Crop residue is traditionally measured using ground survey techniques such as the line-transect method or visual (drive-by) assessment but these techniques are tedious, time-consuming and subjective. With the increased number of advanced earth observation satellites, remote sensing has now become a viable option for mapping agricultural land management practices and percent crop residue cover. A wide variety of indices such as the Normalized Difference Index (NDI) and the Modified Soil Adjusted Crop Residue Index (MSACRI) were developed using multispectral data for this purpose but results have been mixed. Advanced classification techniques including linear spectral mixture analysis (SMA) and spectral angle mapper (SAM) provide an alternative to derive percent crop residue cover. Landsat-7 SLC-Off data were acquired over an agricultural study site in Eastern Ontario on May 25 2005. Simultaneous ground data were collected to characterize residue type, position, direction and percent cover. NDI, MSACRI, SMA and SAM were all computed and used to derive percent crop residue cover information. Preliminary results indicate that the SMA model predicts percent crop residue cover over agricultural fields with the most success, especially over fields of corn residue with an R2 value of 0.85 (RMSE of 12.46 and D of 0.99). However, further investigation is needed where residue models are validated against a larger dataset with greater variability in percent crop residue cover.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".