Machine Learning-aided Multi-physics Identification and Characterization of REE-CM Hot Zones in Mine Tailings for Economic Recovery — Lawrence Berkeley National Laboratory (Berkeley, California) intends to develop a machine learning (ML)-aided multi-physics approach for rapid identification and characterization of rare earth elements (REE) and other critical minerals (CM) hot zones in mine tailings for efficient recovery with a focus on coal and sulfide mine tailings and other processing or utilization byproducts, such as fly ash and refuse deposits. This proposed multi-physics approach integrates a range of advanced and novel geophysical, radiological, and optical technologies deployed on aerial and surface platforms suitable for REE-CM prospecting. Aided by multiple existing and emerging core and lab analytical technologies, this integrated approach provides a cross-scale capability from whole tailing REE-CM hot zone identification to mineralogical and REE-CM characterization and quantification.
DOE Funding: $1,200,000
A Machine Learning Screening Tool for REE and CM at the Mine Scale — Los Alamos National Laboratory (Los Alamos, New Mexico) plans to work with partners at the Wyodak coal mine in the Powder River Basin of Wyoming to develop a ML tool for mine-scale assessment of REE-CM. The project’s mine-scale approach complements the basin-wide assessment of REE-CM in the basin, enabling a telescoping approach to REE-CM assessment. The data will form a new high-resolution dataset in 3D that will then be integrated into a ML training dataset to better characterize the mine-scale distribution of REE-CM and better assess economic viability.
DOE Funding: $1,200,000
Drone-Based Geophysical Surveying and Real-Time AI/ML Analysis for Sustainable Production of Critical Minerals — Pacific Northwest National Laboratory (Richland, Washington) plans to develop and demonstrate drone-based geophysical and remote-sensing technologies to quantify CMs in coal, coal-related, and unconventional and secondary sources or energy-related waste streams. Drone-based geophysical surveys and remote sensing combined with artificial intelligence (AI) and ML for real-time integration and analytics has potential to transform characterization and monitoring for CMs from conventional and secondary resources. Sensor technologies, modeling and data analysis capabilities developed would be agnostic with respect to drone platform and, in principle, could be deployed on ground-based robotic mining or excavation equipment.
DOE Funding: $1,200,000
Resource Assessment of Unconventional Oil and Gas Shale for Critical Minerals Recovery — Sandia National Laboratories (Albuquerque, New Mexico) plans to assess the extractability of CMs, including REEs and precious and transition metals, from major oil and gas shale formations across the United States. Specifically, the team intends to assess the in-situ extractability of these metals using their newly developed extraction system. If successful, the proposed in-situ leaching concept can be directly integrated into existing oil and gas production and field facilities to mine CMs and other metals from shale. The proposed work includes integrated material characterization, batch leaching, and core flow though experiments, thermodynamic modeling of metal speciation, and machine learning for data correlation. This work will establish the technical basis and predictive capabilities to characterize and assess mineralogy and quantity of REEs and CMs more effectively and efficiently in shale formations.
DOE Funding: $1,200,000
Characterization and Extraction of Critical Minerals from Energy Production Waste Streams — SLAC National Accelerator Laboratory (Menlo Park, California) plans to characterize drill cuttings derived through the entire drilling process, identify speciation of CMs and their overall composition in the feedstock, and use this information to develop extraction protocols that are rapidly adaptable by industry. The team also intends to assess the impact of industrial cleaning protocols for removing drilling fluids from the cuttings (both water- and diesel-based) on alterations to the CMs contained in the material, its impacts on developing extraction protocols, and if CMs are being removed and discarded during washing. Tasks will be designed to produce knowledge and extraction protocols for rapid dissemination of findings to the academic and industrial communities for quick adoption into production streams.
DOE Funding: $500,000