Data-Driven Modeling of Limestone Drillability as a Function of Chemical Composition: A Case Study of the Gboko Deposit, Nigeria

This research presents a comprehensive study on the influence of limestone chemical composition on drilling performance in quarry operations. Limestone remains the principal raw material in cement production, and understanding its drillability is critical for optimizing mining efficiency and reducing operational costs. Despite existing qualitative knowledge, there is a notable gap in quantitative predictive modeling linking chemical composition to drilling rate.In this study, we developed and evaluated predictive models using three advanced machine learning techniques: Gaussian Process Regression (GPR), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Support Vector Machine (SVM). The novelty of this work lies in integrating machine learning approaches with geochemical data to predict drilling performance, providing a practical decision-support tool for mine planning, drilling optimization, and cost estimation in limestone quarry operations.