MateriAlZ Seminar: Taylor Sparks
Friday, April 15, 2022, 11:00 a.m. MST
Taylor Sparks
Associate Professor
Deparment of Materials Science and Engineering Department
University of Utah
"Materials Informatics: Moving Beyond Screening via Generative Machine Learning Models"
Zoom Link | Passcode: 288857
MateriAlZ Seminar website | YouTube | Twitter
Abstract
Technology progresses only as fast as the development of new, advanced materials. Materials discovery has never been more important, but it is far too slow and expensive. Materials informatics has accelerated materials development, but primarily allows us to screen known materials as opposed to truly discovering new materials. Here, I will describe our efforts to create new generative models for materials discovery. First, I will describe an approach inspired by neural style transfer where pre-trained models are frozen and the input vector is tuned via gradient descent and black-box optimization to discover new materials with target properties. Second, I will discuss how we are creating new periodic crystalline materials by predicting crystallographic information file data using generative adversarial networks. Finally, I will describe our recently published DiSCoVeR algorithm that combines a chemical distance metric, density-aware dimensionality reduction, clustering, and a regression model to find new materials that are also unlike other materials in the training dataset.
Bio
Dr. Sparks is an associate professor of the Materials Science and Engineering Department at the University of Utah. Before graduate school he worked at Ceramatec Inc. He did his MS in materials at UCSB and his Ph.D. in applied physics at Harvard University and then did a postdoc in the Materials Research Laboratory at UCSB. He is currently the director of the ReUSE REU at the University of Utah and teaches classes on ceramics, materials science, characterization, and technology commercialization. His current research centers on the discovery, synthesis, characterization, and properties of new materials for energy applications. He is a pioneer in the emerging field of materials informatics, whereby big data, data mining, and machine learning are leveraged to solve challenges in materials science. He was a recipient of the NSF CAREER Award and a speaker for TEDxSaltLakeCity. When he’s not in the lab, you can find him running his podcast "Materialism" or canyoneering with his 4 kids in southern Utah.