MSE Colloquium: Brian DeCost, Autonomous systems for alloy design: prototype systems and future opportunities

Abstract

Autonomous research systems continually learn by adaptively planning and executing campaigns of physical and/or in silico experiments to achieve a scientific or engineering goal without direct human intervention. This emerging research area presents new opportunities to accelerate materials synthesis, evaluation, and hence discovery and design. These opportunities critically depend on creative re-evaluation of our current palette of high throughput materials synthesis and characterization tooling in light of new automated perception and planning capabilities enabled by application of machine learning methods.

In this colloquium, I will present two exemplar autonomous systems for alloy design that I am helping to develop at NIST, focusing on technical and methodological aspects of building and deploying robust closed-loop synthesis and characterization platforms. The first is an autonomous X-ray diffraction system that performs active cluster analysis to efficiently map composition-temperature phase diagrams using composition spread thin films. The second is an autonomous scanning droplet cell (ASDC) designed for on-demand alloy electrodeposition and real-time electrochemical characterization for investigating the corrosion-resistance properties of multicomponent alloys. Our initial studies focus on systems that are likely to form corrosion-resistant metallic glasses and single-phase multi-principle element alloys.

Bio

Brian DeCost is a Materials Research Engineer working in the Materials for Sustainable Energy and Development group at the National Institute of Standards and Technology (NIST). He earned a Ph.D. in Materials Science and Engineering at Carnegie Mellon University working with Professor Elizabeth Holm. His Ph.D. and postdoctoral research at CMU developed novel applications of modern computer vision for the automated microstructure analysis. Brian's current research focuses on developing and applying machine learning methods and automation tools to address fundamental and applied problems in microstructure science and alloy design, with emphasis on active learning for autonomous experiment planning and execution.