Crop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information
Bibliographic record
Abstract
Accurate monitoring of croplands helps in making decisions (for insurance claims, crop management and contingency plans) at the macro-level, especially in drylands where variability in cropping is very high owing to erratic weather conditions. Dryland cereals and grain legumes are key to ensuring the food and nutritional security of a large number of vulnerable populations living in the drylands. Reliable information on area cultivated to such crops forms part of the national accounting of food production and supply in many Asian countries, many of which are employing remote sensing tools to improve the accuracy of assessments of cultivated areas. This paper assesses the capabilities and limitations of mapping cultivated areas in the Rabi (winter) season and corresponding cropping patterns in three districts characterized by small-plot agriculture. The study used Sentinel-2 Normalized Difference Vegetation Index (NDVI) 15-day time-series at 10 m resolution by employing a Spectral Matching Technique (SMT) approach. The use of SMT is based on the well-studied relationship between temporal NDVI signatures and crop phenology. The rabi season in India, dominated by non-rainy days, is best suited for the application of this method, as persistent cloud cover will hamper the availability of images necessary to generate clearly differentiating temporal signatures. Our study showed that the temporal signatures of wheat, chickpea and mustard are easily distinguishable, enabling an overall accuracy of 84%, with wheat and mustard achieving 86% and 94% accuracies, respectively. The most significant misclassifications were in irrigated areas for mustard and wheat, in small-plot mustard fields covered by trees and in fragmented chickpea areas. A comparison of district-wise national crop statistics and those obtained from this study revealed a correlation of 96%.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".