Convolutional neural network and transfer learning based mineral prospectivity modeling for geochemical exploration of Au mineralization within the Guandian-Zhangbaling area, Anhui Province, China

摘要

The Zhangbaling-Guandian area is located in the eastern part of Anhui Province, China, and contains several small Au-Cu deposits and occurrences that highlight the prospectivity of this area for future mineral exploration. Recent research has determined that machine learning can identify potentially mineralization-related geochemical anomalies that represent targets for mineral exploration. However, the majority of this previous research has focused on identifying geochemical anomalies based on individual sample points but has not incorporated associated data such as the spatial characteristics of the shape, overlap, and zonation within multivariate geochemical anomalies and haloes. Here, we present a convolutional neural network algorithm based approach to identify areas prospective for Au exploration based on the multielement geochemical maps. This approach considers various spatial characteristics and employs a transfer learning method to reduce the influence of the limited number of known deposits and occurrences in this area, accelerating convergence rates and improving the accuracy of the model. The training results indicate that the accuracy of each training model is >99 and cross-entropy loss values are < 0.1. The results for the entirety of the study area indicate that about 88% of the known mineralization and mineralized occurrences are located in the prospective areas identified during this study. These results indicate that combining geochemical data with an approach employing convolutional neural network algorithms and transfer learning methods can effectively outline the Au mineralization prospectivity of relatively unexplored regions. This indicates that this type of approach could be a useful addition for future mineral exploration using geochemical data. In addition, the use of convolutional neural network approaches yields more accurate identification of geochemical anomalies and can include more geochemical variables, meaning that more geochemical data can be used in convolutional neural network-based approaches to target identification and mineral prospectivity modeling than is used in conventional geochemical anomaly identification.