Litcius/Paper detail

Mineral grade estimation using gradient boosting regression trees

Umit Emrah Kaplan, Yasin Dağaşan, Erkan Topal

2021International Journal of Mining Reclamation and Environment28 citationsDOI

Abstract

Resources estimation is one of the critical tasks to evaluate the economic feasibility of a mineral deposit. Traditional prediction workflows, which often involve kriging and inverse distance weighting methods, may not always be suitable to estimate mineral grades for every type of mineralisation. In this study, we present a grade estimation workflow using gradient boosting-based machine learning methods, namely, XGBoost, LightGBM and CatBoost. The case study demonstrated that the three gradient descent-based models performed better than the OK method. XGBoost model demonstrated the best estimation performance with an R2 of 0.728 accuracies, whereas traditional Ordinary Kriging (OK) model yielded 0.651 for R2.

Topics & Concepts

KrigingGradient boostingBoosting (machine learning)RegressionWeightingWorkflowComputer scienceEstimationInverse distance weightingDecision treeArtificial intelligenceStatisticsData miningMachine learningMathematicsRandom forestEngineeringMultivariate interpolationDatabaseRadiologyMedicineSystems engineeringBilinear interpolationMineral Processing and GrindingGeochemistry and Geologic MappingHydrocarbon exploration and reservoir analysis