This week's speaker is:

William Xu, PhD Candidate, Materials Science and Engineering, Stanford University
"Adaptive Mineral Blending and Routing Using Reinforcement Learning"

Abstract:

Efficient mineral processing is vital to sustainably source the critical minerals needed for national security and the clean energy transition. Ore variability is a major source of uncertainty that limits mineral processing performance and is often addressed by blending feedstocks together to make them more homogenous and consistent. In this work, I use reinforcement learning to solve the problem of feedstock blending and routing under uncertainty in the context of phosphate mining operations in Morocco.

Bio:

William Xu (he/him) is a PhD candidate in Materials Science and Engineering in the Mineral-X research group (supervised by Prof. Jef Caers). He applies AI to optimize mineral processing under uncertainty with the goal of making processing more efficient and sustainable. As a RAISE fellow, William is working with Imperial Valley Equity and Justice to devise community-centered economic development plans in the “Lithium Valley” region of southern California.

The topics of this seminar are broad but typically fall under technologies’ scaling potential and impact on (the system of) people, the environment and the economy. A particular focus is placed on the interaction potential of technologies with the energy, water, and material systems. Our goal is to create an intimate, collaborative space for students, postdocs, scientists, and PIs within Stanford across micro-level (material and technology) to macro-level (system) interests. These seminars will provide an opportunity to disseminate insights from your studies, connect with fellow researchers, and strengthen bonds across the community.