Compositional data analysis in the study of integrated geochemical anomalies associated with mineralization

Abstract

Geochemical data are typical compositional data which should be opened prior to univariate and multivariate data analysis. In this study, a frequency-based method (robust principal component analysis, RPCA) and a frequency-space-based method (spectrum–area fractal model, S–A) are applied to explore the effects of the data closure problem and to study the integrated geochemical anomalies associated with polymetallic Cu mineralization using a stream sediment geochemical dataset collected from the Zhongteng district, Fujian Province (China). The results show that: (1) geochemical data should be opened prior to RPCA to avoid spurious correlation between variables; (2) geochemical pattern is a superimposition of multi-processes and should be decomposed; and (3) the S–A fractal model is a powerful tool for decomposing the mixed geochemical pattern.