LAUSR

Abstract In this study, a GANomaly network was used to detect geochemical anomalies related to mineralization in the southern part of Jiangxi Province and its adjacent areas in China. The training data used in this study belong to a typical rare-sample category of imbalanced data samples; thus, during the training phase, only non-mineralized dataset randomly selected from the study area was used for training in order to avoid the overfitting problem caused by an imbalance between positive and negative training samples. The established GANomaly network structure can effectively extract anomalous geochemical information from the exploration geochemical data. The geochemical anomalies identified by GANomaly and known tungsten polymetallic deposits show a close spatial correlation. Further, the anomalous high-value areas are located in or around the Yanshanian intrusive rock. The performance of GANomaly for the identification of multivariate geochemical anomalies was compared to that of the deep autoencoder. The comparative results indicated that the GANomaly network can learn the internal connections and characteristics between multivariate geochemical data and can effectively avoid the influence of noise in geochemical data. Therefore, the abnormal areas identified by GANomaly are determined to be significant for mineral exploration.