APPLIED MACHINE LEARNING IN MINERAL PROSPECTIVITY MAPPING IN THE SOUTH PASS-GRANITE MOUNTAINS, WYOMING

The South Pass Granite Mountains, comprised of Archean to Tertiary rocks embedded with an Archean greenstone belt in Central Wyoming, have historically been mined for gold, iron, steel, and silver. Rare earth elements have been of increasing interest in the region and thus, several datasets have become available. Knowledge driven and data driven models are used in mineral prospectivity mapping with input data including geological mapping, geochemical data, geophysical (USGS Critical Mineral magnetic and gravity data), radiometric (U, Th, K) data and multispectral remote sensing data. Mineral prospectivity has seen a rapid improvement in recent years using advancements in machine learning for processing large and complex datasets to identify new potential deposit locations. The magnetic and gravity data will be utilized to create lineaments that may act as conduits for ore fluids and for fault density evidential maps for input into the machine learning algorithms. This study aims to utilize and compare algorithms such as Random Forest, Light Gradient Machine Boosting, Support Vector Machine, and Convolutional Neural Networks on evidential maps to identify potential new gold and rare earth element deposits within the South Pass region.