Self-Organizing Maps Analysis of Chemical–Mineralogical Gold Ore Characterization in Support of Geometallurgy

Few studies have been published on the analysis and correlation of data from process mineralogical gold ore employing artificial neural networks (ANNs). This study aimed to analyse investigate correlations obtained by technological characterization auriferous using an ANN called self-organizing map (SOM) support geometallurgical studies. The SOM is a technique in which patterns relationships within database are internally derived outputs visual, assisting understanding representation 2D maps. In generated, it was possible establish that variables accessibility, exposed perimeter, median grain diameter (D50), SiO2 arsenic contents strong positive correlations. Regarding geometallurgy, this shows can identify large-scale spatial chemical–mineralogical patterns, help define most relevant indicator for mineral processing.