Data-Driven Synthesis of a Geometallurgical Model for a Copper Deposit

Abstract

Geometallurgy integrates aspects of geology, metallurgy, and mine planning in order to improve decision making in mining schedules. A geometallurgical model is a 3D space that is typically synthesized from early-stage small-scale samples and is composed of several metallurgical units, or domains. This work explores the synthesis of a geometallurgical model for a copper deposit using a purely data-driven unsupervised approach. To this end, a dataset of 1112 drill samples is used, which are clustered using different methods, namely, k-means, hierarchical clustering (AGG), self-organizing maps (SOM), and DBSCAN. Two cluster validity indices (Silhouette and Calinski–Harabasz) are used to select the final model. To validate the potential of the proposed approach, a simulated economic evaluation is conducted. Results demonstrate that k-means exhibits a better performance in terms of modeling and that using the obtained geometallurgical model for mining scheduling increases the project’s Net Present Value (NPV) by as much as 4%. Based on these results, the proposed methodology is an appealing alternative for generating geometallurgical models within greenfield, brownfield and ongoing operations.

Geometallurgical Simulation of the Work Index in a Porphyry Copper Deposit Using Geostatistical Techniques

“…Geometallurgy incorporates geological, metallurgical, mine planning information to improve decision making in mining projects (Mu & Salas, 2023), for which it makes use of primary and response variables (Castro et al, 2022), and predictive spatial models (Castillo et al, 2022).…”

Evaluation of PCA with variable selection for cluster typological domains

“…The study of variable selection problems dates back more than 50 years (Roy, 1958, Efroymson, 1960Beale et al, 1967apud Brusco, 2014 and continues to be a relevant topic with recent contributions. In mining, some current work is being done using PCA associated with other machine learning techniques: to reduce geometallurgical variables in neural network models (Mu, 2023); to identify variables that best correlate in geometallurgical studies in a gold mine using self-organizing map clustering (Costa, 2023); in models for predicting water inrush in coal mines using neural networks (DBN) in order to reduce the long training time (Zhang, 2022); in work on the spatial autocorrelation of geotechnical information to reduce the increasing dimensionality of the data set caused by the EDF-Euclidean distance…”

Simulating the Impact of Ore and Water Quality on Flotation Recovery during the Life of a Mine

“…In general, a higher ore head grade typically results in a higher grade and recovery at the concentrator. The concept of geometallurgy has been defined around 1970 [1]. The geometallurgical approach that combines geological and metallurgical information has been applied in mine planning and plant design with varying success for some decades [2].…”