Automatic Cross-Region Near-Real-Time Crop Type Mapping with Image Segmentation Through Supervised Learning Method
Bibliographic record
Abstract
The Automatic Cross-Region Near-Real-Time Crop Type Mapping with Image Segmentation Through Supervised Learning Method (ACCMSS) model provides a versatile approach for the automated mapping and classification of crop types using Sentinel-2 multispectral imagery, employing image segmentation through a supervised learning technique in near real-time. It integrates scene classification with pixel-level segmentation and implements Google Earth Engine (GEE) for preprocessing, including cloud removal and spectral analysis. The approach utilizes the Within-Season Emergence (WISE) model to monitor crop phenology through an NDVI analysis and Class Activation Maps (CAM) refined with a specialized segmentation method. To reduce misclassification of crops, reinforce their adaptability to various datasets from regions like Spain and Switzerland. The ACCMSS model is characterized by its agricultural conditions and a modular design conducive to application in diverse geographies. The following metrics are calculated to show how better our ACCMSS model is than the existing models, MCNBS, NACYP, and SICSU. The accuracy of 97 %, the F1-Score of 91 %, the precision of 91 %, the recall of 94 %, and the confusion matrix of the ACCMSS model is 2471.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".