RARE EARTH ELEMENTS – MULTIPHYSICS AI-AIDED AUTONOMOUS PROSPECTING (REE -MAP)

Field scale mapping of Rare Earth Elements and Critical Minerals (REE-CM) in unconventional and secondary sources presents significant challenges due to low and variable concentrations and the unique characteristics of each source material. Identifying "hot zones," or areas with high REE-CM concentrations, is crucial for assessing the economic feasibility of these sources. This study proposes an AI-aided multi-physics approach for the rapid and autonomous field scale characterization of REE-CM hot zones in mine tailings, focusing on coal. The multi-physics approach integrates advanced geophysical, radiological, and optical technologies deployed on aerial and surface platforms, combined with core and lab analytical methods. This provides a cross-scale capability from whole tailing REE-CM hot zone identification to detailed mineralogical characterization. AI capabilities are key to integrating multi-physics datasets for identifying hot zones and optimizing sensing technology deployment.

Leveraging the expertise at Berkeley Lab across multiple disciplines, we have developed an efficient, autonomous, and economically viable method for REE-CM extraction from secondary sources. Field tests were carried out at coal refuse and ash sites in Pennsylvania were carried out to explore the correlation between multi-physical signals and REE concentrations, with a goal of demonstrating the feasibility of such an approach. Successful implementation will enhance the economic viability of REE-CM recovery, guiding the prioritization of extraction efforts.