Optimization of leaching efficiency and anomaly detection in a copper–cobalt hydrometallurgical plant using random forest, gradient boosting, and k-nearest neighbors

Hydrometallurgical extraction of copper (Cu) and cobalt (Co) from oxide ores represents a critical industrial process in the Central African Copperbelt, yet operational variability consistently undermines recovery targets. This study presents a comprehensive data-driven analysis of six months (July–December 2024) of daily operational records from an industrial 8,000-tonne-per-day Cu–Co hydrometallurgical plant located in the Democratic Republic of Congo (DRC). A total of 177 quality-filtered daily observations encompassing 23 process variables were systematically preprocessed, analyzed, and modeled. These variables include crushing and grinding throughput, particle size distribution (PSD), leach feed thickener (LFT) and leach discharge thickener (LDT) parameters, countercurrent decantation (CCD) underflow densities, pregnant leach solution (PLS) concentrations, free sulfuric acid (H 2 SO 4 , hereafter free acid, g/L), pH, and electrowinning efficiency. Three machine learning algorithms were deployed: Random Forest (RF), Gradient Boosting (GB), and K-Nearest Neighbors (KNN). Under 5-fold walk-forward cross-validation on normal operating folds (excluding the October 2024 maintenance shutdown period), RF achieved mean Cu R 2 = 0.698 ± 0.236 and Co R 2 = 0.780 ± 0.175, while GB achieved mean Cu R 2 = 0.641 ± 0.126 and Co R 2 = 0.795 ± 0.190. On the independent December 2024 temporal holdout test set, RF achieved Cu RMSE = 0.807% (R 2 = 0.583) and Co R 2 = 0.922 (RMSE = 3.74%), while GB achieved Cu RMSE = 0.851% (R 2 = 0.537) and Co R 2 = 0.932 (RMSE = 3.48%). RF provided the most reliable discrimination of daily Cu target (≥94%) achievement among the three models (AUC = 0.867, accuracy = 69.6%, F1 = 0.788). The Cu residue ratio, average CCD underflow density, mill throughput, and high-grade PLS (HG PLS) Cu concentration were identified as the dominant predictors of leaching efficiency. Cu leaching met the ≥ 94% target on 72.2% of operating days, whereas the more challenging Co target of ≥ 80% was achieved on only 40.3% of days. High free acid episodes (>8 g/L) were recorded on 61.0% of days, with a statistically significant negative association with Co recovery. Response surfaces for process optimization generated from RF and GB predictions identify operating windows of HG PLS Cu > 10.5 g/L and free acid < 8 g/L as necessary conditions for simultaneously achieving both leaching targets. These findings provide actionable, evidence-based guidance for optimizing plant performance and reducing operational variability in complex Cu–Co hydrometallurgical circuits.