Date of Award

Fall 2019

Document Type

Open Access Dissertation

Department

Chemical Engineering

First Advisor

Jochen Lauterbach

Abstract

Advances in artificial intelligence technology, specifically machine learning, have cre- ated opportunities in the material sciences to accelerate material discovery and gain fundamental understanding of the interaction between certain the constituent ele- ments of a material and the properties expressed by that material. Application of machine learning to experimental materials discovery is slow due to the monetary and temporal cost of experimental data, but parallel techniques such as continuous com- positional gradients or high-throughput characterization setups are capable of gener- ating larger amounts of data than the typical experimental process, and therefore are suitable for combination with machine learning. A random forest machine learning algorithm has been applied to two different materials discovery challenges - discovery of new metallic glass forming ternary compositions and discovery of novel ammonia decomposition catalysts - and has led to accelerated discovery of high-performing materials.

Rights

© 2019, Travis Williams

Share

COinS