Resource-Efficient Material Design Campaigns with Artificial Intelligence

Speaker: Logan Ward, Argonne National Laboratory

Abstract
Materials design requires being judicious about how to use resources. Careful thought and analysis on how new data should inform the next experiment or computation is the key to success. However, the continual arrival of increasingly faster ways of gathering data (e.g., exascale supercomputers, robotic laboratories) leaves much shorter times for engineers to be circumspect. In this talk, we discuss how artificial intelligence systems can augment human ability to design and execute experiments with a focus on developing new battery electrolytes and accelerating the testing of battery cells. We will focus on both the fundamental and nuances of how to create the required AI tools, as well as the foundational software advances needed to support an AI-enhanced future of materials design.

Bio
Logan Ward is an Assistant Computational Scientist at Argonne National Laboratory in the Data Science and Learning Division. He earned a BS/MS from The Ohio State University in 2012 and a PhD in Materials Science of Engineering from Northwestern University in 2017. His thesis work focused on developing machine-learning-based techniques for predicting material properties. Since beginning as a post-doc in the Computation Institute at the University of Chicago, he has worked towards making such machine learning approaches more accessible to all scientists. Most of Logan’s projects are to develop the methods, software, data infrastructure, and educational materials needed for pervasive AI in the physical sciences.