Exploration
Marco Antonio Cotrina Teatino; Jairo Jhonatan Marquina-Araujo; Jose Nestor Mamani-Quispe; Solio Marino Arango-Retamozo; Joe Alexis Gonzalez-Vasquez
Abstract
The geochemical and spatial characterization of legacy mine tailings is essential for identifying reprocessing opportunities and informing environmental management. However, the high compositional complexity of polymetallic tailings requires robust multivariate approaches. This study evaluates and compares ...
Read More
The geochemical and spatial characterization of legacy mine tailings is essential for identifying reprocessing opportunities and informing environmental management. However, the high compositional complexity of polymetallic tailings requires robust multivariate approaches. This study evaluates and compares the performance of four unsupervised clustering algorithms Euclidean K-Means, Riemannian K-Means, Gaussian Mixture Model (GMM), and Agglomerative Clustering applied to 927 samples from the Quiulacocha tailings deposit in Peru, using six major elements (Zn, Pb, Cu, Fe, Ag, Au) and spatial coordinates. All methods consistently identified three main geochemical domains. Cluster 1 was enriched in Cu and Au, Cluster 2 in Pb and Fe, and Cluster 3 in Zn, Ag, and Fe. Covariance-based methods (Riemannian K-Means and Agglomerative Clustering) outperformed others in internal validation (Silhouette scores up to 0.58) and consistency (Adjusted Rand Index = 1.00), offering more interpretable and geologically coherent partitions. CLR transformation reduced clustering performance, highlighting the importance of preserving raw geochemical variance for spatial segmentation. These findings demonstrate the effectiveness of multivariate clustering for unraveling compositional heterogeneity in tailings and delineating domains of potential economic value. The approach provides a quantitative framework for supporting reprocessing decisions, reducing risk, and guiding future research on mine waste valorization.
