ChE Seminar Series: Materials Innovation in Nanotechnologies

ChE Seminar Series Presents:

Dr. Paulette Clancy, Ph.D
Head of the Department of Chemical and Biomolecular Engineering at Johns Hopkins University

Materials Innovation in Nanotechnologies

Abstract
There are many problems at the forefront of materials chemistry whose solution is stymied by its inherent complexity. Such problems are characterized by a rich landscape of parameters and processing variables that is combinatorially too large for either an experimental or a computational approach to solve through an exhaustive search. In such cases, the usual approach is an Edisonian trial-and-error approach, which inevitably leaves areas of parameter space unexplored. The problems that we have explored are also characterized by a scarcity of data, since the data are expensive to acquire, both experimentally and computationally. This makes it an ideal candidate to solve using a Bayesian optimization (BayesOpt) approach.
We have used a Bayesian approach to study several problems in self-assembly processes involving materials chemistry. This talk will discuss two mature test cases in which we used BayesOpt extensively to study (1) how to optimize the choice of solvent and halides to produce high quality thin films of lead-based hybrid organic-inorganic perovskites and (2) identify stable and metastable polymorphs of an organic semiconducting material. I will end with some ideas of where the BayesOpt field can expand its use in the chemical sciences and share some “lessons learned” in implementing BayesOpt and machine learning, which may be helpful to others who decide to start adding machine learning to their research repertoire.

Biography
Paulette Clancy is a Professor and the inaugural Head of the Department of Chemical and Biomolecular Engineering at Johns Hopkins University. She is also the Samuel and Diane Bodman Professor Emerita of Chemical Engineering at Cornell. She is the Associate Director of the Hopkins Center for Integrated Structure-Materials Modeling and Simulation. She was the inaugural Director of the Cornell Institute for Computational Science and Engineering for almost 10 years and is reprising a similar role at Hopkins, chairing our petascale research computing resources, ARCH.
Her research group is recognized as one of the country’s leading computational groups in atomic- scale modeling of materials and algorithm development. Her current thrust is to develop machine learning algorithms to accelerate the search for optimal materials processing protocols. Her group has always been focused on electronic materials, but it also includes more esoteric projects include xenobiology (Life on Titan) and a screening of therapeutic oligomers to maximize antibacterial ability. She has won numerous awards for mentoring, service learning and civic engagement, and promoting those from under- represented groups.