SOC_metadata

The ensemble model showed strong predictive performance (R² = 0.86, RMSE = 0.11) and generalized well across a wide range of conditions. Shapley Additive exPlanations (SHAP) analysis identified biochar addition rates, crop types, and soil pH were the most influential predictors of SOC changes. Partial dependence plots revealed nonlinear and threshold effects of pyrolysis temperature, initial SOC levels, and nitrogen content. This work highlights the predictive power and interpretability of ML tools in digital soil carbon modeling and supports data-driven strategies for optimizing biochar use in climate-smart agriculture.