Identifying geochemical anomalies associated with Au–Cu mineralization using multifractal and artificial neural network models in the Ningqiang district, Shaanxi, China

Abstract The Ningqiang district, which is located in the northwestern margin of the Yangtze Platform, contains the richest supply of Cu and Au mineral resources in Shaanxi Province, China. The purpose of this study is to identify geochemical anomalies associated with Au–Cu mineralization in the Ningqiang mineral district using spectrum–area (S–A) multifractal and artificial neural network (ANN) methods. The centered logratio ( clr ) transformation was applied to preprocess geochemical data which contain 226 samples with concentrations of Zn, Au, Ag, As, Ba, Bi, Cu, Hg, Mo, Sb, Pb, and W. The processed geochemical data are then further examined by means of factor analysis (FA) to explore statistically the data regarding geochemical patterns and to assist the identification and interpretation of element associations. The resulting S–A based on the Factor 2 obtained by FA suggests that the geochemical patterns of Cu and Au are linked with the Bikou Group, which may be the source of metal for the formation of mineralization. The predictive results obtained by ANN are in good agreement with the known deposits, indicating that ANN methods are capable of managing nonlinear relationships properly. The integrated methods of FA, S–A, and ANN demonstrated in this study are useful in identifying anomalies associated with Cu and Au mineralization for further exploration of mineral resources. In addition, these methods also confirm that the NE-oriented structures and the Second-rock Formation of the Bikou Group are two key factors for the formation of Au–Cu mineralization in the study area.