Critical Minerals, Metals, and Materials (CMMM)

Innovative Materials Chemistry for Sustainable Minerals, Metals, and Materials, and Resource Recovery

Machine Learning–Enabled Smart Materials and Manufacturing for Critical Mineral Extraction, Recovery, and Separation

Jing Tang, assistant professor of mechanical engineering, leads this project that aims to improve extraction, separation, and recovery techniques for critical minerals by developing machine learning-enabled smart materials and manufacturing strategies.

Minerals such as rare earth elements, resources derived from mineral-rich brines and seawater, mined ores, waste tailings, metals recovered from electronic waste, and critical battery materials, are indispensable to clean energy systems, electric vehicles, and national defense technologies. However, existing extraction, recovery, and separation processes are energy-intensive, environmentally burdensome, and susceptible to global supply chain disruptions.

“We are combining advanced materials design with artificial intelligence tools to rapidly identify highly selective separation materials and optimize processing conditions,” Tang explained. “By integrating data-driven modeling with experimental validation, we aim to create more efficient, lower-energy, and more sustainable recovery pathways.”

Mineral extraction and separation are foundational processes that influence the cost, quality, and sustainability of final products, Tang explained. If the foundational process can be effectively optimized, consumers of final products will benefit.

The team is developing models that can forecast material performance and guide experimental design, ultimately accelerating discovery and lowering costs by reducing the need for traditional trial-and-error experimentation. By embedding these models into process design and optimization, they aim to encourage the emergence of adaptive, data-driven manufacturing systems that are economically competitive and environmentally responsible.