Abstract: The challenges faced in developing new electrolyte materials are common in many other design problems. Materials with the desired properties are rare, computations needed to assess candidate materials are slow, and the experiments too expensive to evaluate any significant fraction of the search space. Presented with these challenges, we envision integrating several classes of artificial intelligence together to perform simulations autonomously on exascale supercomputing resources.

In this talk, we highlight the diverse range of issues and recent progress toward bringing this vision into reality. We will focus on suite of machine learning models developed at Argonne to predict a variety of properties of electrolytes and our progress towards coupling these algorithms with quantum chemistry calculations.

Bio: Logan Ward is an assistant computational scientist at Argonne National Laboratory. He earned a Ph.D. in materials science and engineering from Northwestern University. He currently works on a variety of projects that integrate machine learning with physical sciences.