High-resolution field-scale mapping of soil organic matter using multi-temporal Sentinel data and machine learning approach
Bibliographic record
Abstract
Accurate mapping of soil organic matter (SOM) at the field scale is crucial for precision agriculture and sustainable soil management. While remote sensing has shown promise for digital soil mapping, most studies focus on regional scales, leaving a gap in high-resolution field-scale applications. This study explores the potential of multi-temporal Sentinel-2 (optical) imagery for SOM prediction at the field scale. Two machine learning algorithms Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were compared through appropriate validation and uncertainty quantification approaches. RF demonstrated superior performance (R² = 0.939, RMSE = 0.166, LCCC = 0.897) compared to XGBoost (R² = 0.885, RMSE = 0.167, LCCC = 0.903). Uncertainty analysis through 90% Prediction Interval Width (PIW 90) revealed more consistent predictions for RF models. This study demonstrates the feasibility of high-resolution SOM mapping using optical satellite time series data at the field scale, providing a framework for precision agriculture applications. The methodology developed provides a framework for detailed spatial assessment of SOM variability at the field scale, enabling farmers to understand soil patterns and implement targeted management strategies based on high-resolution predictions. All data and code used in this study are made publicly available to ensure reproducibility and facilitate further research. • Sentinel-2 time series enabled accurate SOM mapping at 10 m. • Random Forest outperformed XGBoost with lower uncertainty. • SHAP improved model interpretability and revealed key predictors. • The approach supports precision agriculture with open satellite data.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 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".