Detection of the multivariate geochemical anomalies associated with mineralization using a deep convolutional neural network and a pixel-pair feature method

Abstract

Machine learning (ML) algorithms are widely applied in various fields owing to their strong ability to abstract high-level features from a large number of training samples. However, few supervised ML algorithms have been applied in geochemical prospecting and mineral exploration because mineralization is a rare geological event that leads to an insufficient number of training samples. Generating a large number of training samples is crucial for the application of supervised ML in geochemical prospecting and mineral exploration. In this study, a novel anomaly detection framework combined with a pixel-pair feature (PPF) method and a deep convolutional neural network (CNN) was employed to identify the multivariate geochemical anomalies associated with mineralization. First, the PPF method was employed to generate sufficient training samples by recombining the pixel pairs of the labeled samples. Then, a multilayer supervised CNN framework, which consists of 13 convolutional layers, an average pooling layer, and a fully connected layer, was trained with these pixel pairs for geochemical anomaly recognition. The testing procedure was based on the fact that neighboring pixels belong to the same class with a high probability. The dual-window detector was applied to detect multivariate geochemical anomalies related to Fe polymetallic mineralization in the southwest Fujian Province of China. The identified geochemical anomalies exhibited a close spatial correlation with the known mineral deposits, which validates the potential of the proposed method. Therefore, the method developed in this study can enhance the application of supervised ML in geochemical prospecting and mineral exploration.