Application of Machine Learning to optimize Gold recovery during Cyanide Leaching at Wagagai gold mine
| dc.contributor.author | Ayebale, Reyes | |
| dc.date.accessioned | 2026-06-17T14:53:57Z | |
| dc.date.available | 2026-06-17T14:53:57Z | |
| dc.date.issued | 2026 | |
| dc.description.abstract | The cyanide leach process, also known as gold cyanidation, is a hydrometallurgical technique used to extract gold from low-grade ore, yet its efficiency is often compromised by the complex, non-linear interactions among various operational parameters (e.g., cyanide concentration, pH, leaching time, pulp density, and dissolved oxygen). Traditional optimization methods heavily rely on subjective operator experience, leading to suboptimal and inconsistent gold recovery rates.This study addressed this challenge by applying machine learning techniques to predict and optimize gold recovery during cyanide leaching at Wagagai Mining (U) Limited. A dataset of 2801 historical plant records was developed using key process variables, including cyanide concentration, pH, leaching time, pulp density, and dissolved oxygen. Three models including Multiple Linear Regression (MLR), Random Forest (RF), and Artificial Neural Network (ANN) were developed and evaluated using statistical performance metrics including the coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean Squared Error (MSE). The results showed that the ANN model outperformed the others, achieving the highest predictive accuracy with an R² of 0.9444 and RMSE of 1.0209, compared to RF (R² = 0.9133) and MLR (R² = 0.8509). Hyperparameter optimization further improved ANN performance and confirmed that a single hidden layer with 10 neurons was optimal. The optimized ANN predicted a maximum gold recovery of 96.42% at a cyanide concentration of 800 mg/L, pH of 10.67, leaching time of 48 hours, pulp density of 35%, and dissolved oxygen of 12 mg/L. Partial Dependence Plots (PDPs) and sensitivity analysis were used to interpret the model, revealing that pulp density and cyanide concentration are the most influential variables affecting recovery, while pH and dissolved oxygen play significant but moderate roles. Sensitivity analysis revealed that pulp density (10.53) and cyanide concentration (8.004) were the most influential variables. The findings demonstrate that ANN-based models are effective tools for optimizing cyanide leaching and improving operational efficiency in gold mining. | |
| dc.identifier.citation | Ayebale, R. (2026). Application of Machine Learning to optimize Gold recovery during Cyanide Leaching at Wagagai gold mine [Undergraduate Research report]. Busitema University. | |
| dc.identifier.uri | https://bdears.busitema.ac.ug/handle/123456789/6235 | |
| dc.language.iso | en | |
| dc.publisher | Busitema University | |
| dc.title | Application of Machine Learning to optimize Gold recovery during Cyanide Leaching at Wagagai gold mine | |
| dc.type | Thesis |