High-resolution field-scale mapping of soil organic matter using multi-temporal Sentinel data and machine learning approach

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.