Predicting copper leaching from slag: an interpretable machine learning approach under oxidative sulfuric acid conditions

Key Points

• The aim is to model and predict the efficiency of copper leaching from slag using machine learning.
• Utilized an interpretable XGBoost model for prediction.
• Conducted SHAP analysis to identify influential factors.
• Analyzed the effect of time, acid concentration, and temperature.
• Achieved a predictive model with R² = 0.9794.
• Identified time, acid, and temperature as dominant factors affecting leaching efficiency.
• Enabled quantitative optimization for sustainable copper recovery.