Exploitation
Marco Antonio Cotrina Teatino; Jairo Jhonatan Marquina Araujo; Jose Nestor Mamani Quispe; Solio Marino Arango-Retamozo; Johnny Henrry Ccatamayo-Barrios; Joe Alexis Gonzalez-Vasquez; Teofilo Donaires-Flores; Maxgabriel Alexis Calla-Huayapa
Abstract
Mining plays a crucial role in the economy of many countries, contributing significantly to GDP, employment, and industrial development. However, optimizing drilling and blasting operations remains a key challenge in open-pit mining due to its direct impact on operational costs and rock fragmentation ...
Read More
Mining plays a crucial role in the economy of many countries, contributing significantly to GDP, employment, and industrial development. However, optimizing drilling and blasting operations remains a key challenge in open-pit mining due to its direct impact on operational costs and rock fragmentation efficiency. This work aims to optimize fragmentation (X50) and drilling and blasting costs using hybrid machine learning models, an innovative approach that improves predictive accuracy and economic feasibility. Six models were developed: Artificial Neural Networks (ANNs), Decision Trees (DT), Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Regression (SVR), optimized using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The dataset, comprising 100 blasts, was split into 70% for training and 30% for testing. The SVR+PSO model achieved the highest accuracy for fragmentation prediction, with an RMSE of 0.27, MAE of 0.21, and R2 of 0.92. The RF+GA model was most effective for cost prediction, with an RMSE of 414.58, MAE of 354.14, and R2 of 0.99. Optimization scenarios were implemented by reducing burden (4.3 m to 3.8 m) and spacing (5.0 m to 4.5 m), achieving a 5.7% reduction in X50 (17.6 cm to 16.6 cm) and a 9.5% cost decrease (63,000 USD to 57,000 USD per blast). Predictions for 30 future blasts using the RF + GA model estimated a total cost of 1.7 MUSD, averaging 55,180 USD per blast. These findings confirm the effectiveness of machine learning in cost optimization and improving blasting efficiency, presenting a robust data-driven approach to optimizing mining operations.
Exploration
Marco Antonio Cotrina-Teatino; Jairo Jhonatan Marquina-Araujo; Jose Nestor Mamani-Quispe; Solio Marino Arango-Retamozo; Johnny Henrry Ccatamayo-Barrios; Joe Alexis Gonzalez-Vasquez; Teofilo Donaires-Flores; Maxgabriel Alexis Calla-Huayapa
Abstract
This work aimed to categorize mineral resources in a copper deposit in Peru, using a machine learning model, integrating the K-prototypes clustering algorithm for initial classification and Random Forest (RF) as a spatial smoother. A total of 318,443 blocks were classified using geostatistical and geometric ...
Read More
This work aimed to categorize mineral resources in a copper deposit in Peru, using a machine learning model, integrating the K-prototypes clustering algorithm for initial classification and Random Forest (RF) as a spatial smoother. A total of 318,443 blocks were classified using geostatistical and geometric variables derived from Ordinary Kriging (OK) such as kriging variance, sample distance, number of drillholes, and geological confidence. The model was trained and validated using precision, recall, and F1-score metrics. The results indicated an overall accuracy of 97%, with the measured category achieving 98% precision and an F1-score of 0.98. The total estimated tonnage was 5,859.36 Mt, distributed as follows: 1,446.13 Mt (measured), 2,249.22 Mt (Indicated), and 2,164.01 Mt (Inferred), with average copper grades of 0.43%, 0.33%, and 0.31% Cu, respectively. Compared to the traditional geostatistical methods, this hybrid approach improves classification objectivity, spatial continuity, and reproducibility, minimizing abrupt transitions between categories. The RF model proved to be a robust tool, reducing classification inconsistencies and better capturing geological uncertainty. Future studies should explore hybrid models (K-means with RF, ANN with K-Prototypes, gradient boosting, and deep learning) and incorporate economic variables to optimize decision-making in resource estimation.
