Modeling of Underground Mineral Production Using Machine Learning Techniques: A Case Study of Rutongo Mines Limited Cassiterite

This research investigates the application of machine learning for forecasting cassiterite production at the Rutongo Mines Limited Concession using time-series data. This study compares various models and evaluates their performance based on R-squared and Mean Squared Error (MSE). The Gradient Boosting model with an R-squared of 0.72, emerged as the most effective. This study highlights the potential of machine learning, particularly for generating accurate production forecasts, and demon-strates the impact of time-series predictions on enhancing productivity and decision-making in underground mining operations.