Complementarity of Sentinel-1 and Sentinel-2 Data for Mapping Agricultural Areas in Senegal
Bibliographic record
Abstract
The small size of agricultural plots is the main difficulty for crops mapping with remote sensing data in the Sahelian region of Africa. The study aims to combine Sentinel-1 (radar) and Sentinel-2 (Optic) data to discriminate millet, maize and peanut crops. Training plots were used in order to analyse temporal variation of the three crops’ signals. The NDVI (Normalized Difference Vegetation Index) was able to differentiate crops only at the end of the rainy season (October). The optical data as well as the radar ones could not easily discriminate the three crops during the growing season, because in that period vegetation cover is low, and soil contribution to the signals (due to roughness and moisture) was more important than that of real vegetation. However, the ratio of VH/VV (VH: incident signal in vertical polarization and reflected signal in horizontal polarization; VV: incident signal in vertical polarization and reflected signal in horizontal polarization) gave a difference between millet and the two other crops at the beginning cultural season (July 11). Difference appears from the second third of September when the harvest of cereals crops (millet and maize) began. From middle of October, the peanut signal dropped sharply thus facilitating the differentiation of peanut from the two other crops. This analysis led to the identification of data that have could be used to discriminate these crops (useful data). Classification of the combined useful data gave an overall high accuracy of 82%, with 96%, 61% and 65% for peanut, maize and millet, respectively. The non-agricultural areas (water, natural vegetation, habit, bare soil) were well classified with an accuracy greater than 90%.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| 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".