Special Seminar: Combinatorial Experimentation and Machine Learning for Materials Discovery
Ichiro Takeuchi
1:25 PM on 2017-10-17
B-75 Amundson Hall
Throughout the history of mankind, scientists and engineers have relied on the slow and serendipitous trial-and-error approach for materials discovery. In 1990s, the combinatorial approach was pioneered in the pharmaceutical industry in order to dramatically increase the rate at which new medical compounds are identified. The high-throughput concept is now widely implemented in a variety of fields in materials science. We have developed combinatorial thin film synthesis and characterization techniques in order to perform rapid survey of previously unexplored materials phase space in search of new inorganic functional materials with enhanced physical properties. Various physical vapor deposition schemes are implemented for fabricating massive arrays of compositionally varying samples on individual combinatorial libraries. A suite of high-throughput characterization tools including synchrotron diffraction are employed to screen the libraries and map different physical properties. Examples of materials systems we have explored include fatigue-free shape memory alloys, rare-earth free permanent magnets, morphotropic phase boundary piezoelectric materials, magnetostrictive materials, and superconductors. I will discuss applications of machine learning to the combinatorial strategy including our recent effort where active learning is used to design and steer the sequence of experiments in order to maximize attainable knowledge, minimize experimental resources, and as a result further speed up the materials discovery process.
Seminars are open to alumni, friends of the Department, and the general public.