The surging demand for nickel (Ni) and cobalt (Co), driven by the acceleration of clean energy transitions, has sparked interest in the Lachlan Orogen of New South Wales for its potential lateritic Ni-Co resources. Despite recent discoveries, a substantial knowledge gap exists in understanding the full scope of these critical metals in this geological province. This study employs a machine learning-based framework, integrating multi-dimensional datasets to create prospectivity maps for lateritic Ni-Co deposits within a specific Lachlan Orogen segment. The framework generates a variety of data-driven models incorporating geological (rock units, metamorphic facies), structural, and geophysical (magnetics, gravity, radiometrics, and remote sensing spectroscopy) data layers. These models range from comprehensive models that use all available data layers to fine-tuned models restricted to high-ranking features. Additionally, two hybrid (knowledge-data driven) models distinguish between hypogene and supergene components of the lateritic Ni-Co mineral systems. The study implements data augmentation methods and tackles imbalances in training samples using the SMOTE-GAN method, addressing common machine learning challenges with sparse training data. The study overcomes difficulties in defining negative training samples by translating geological and geophysical data into training proxy layers and employing a positive and unlabelled bagging technique. The prospectivity maps reveal a robust spatial correlation between high probabilities and known mineral occurrences, projecting extensions from these sites and identifying potential greenfield areas for future exploration in the Lachlan Orogen. The high-accuracy models developed in this study utilising the random forest classifier enhance the understanding of mineralisation processes and exploration potential in this promising region.
