|About this Abstract
||Materials Science & Technology 2020
||High Entropy Materials: Concentrated Solid Solution, Intermetallics, Ceramics, Functional Materials and Beyond
||Using Machine Learning, CALPHAD, and DFT to Accelerate Materials Development
||Kenneth S. Vecchio, Kevin Kaufmann
|On-Site Speaker (Planned)
For the past decade, considerable research effort has been devoted toward computationally identifying and experimentally verifying single phase, high-entropy systems. However, predicting the resultant crystal structure(s) “in silico” remains a major challenge. Previous studies have primarily used density functional theory to obtain correlated parameters and fit them to existing data. This strategy is impractical given the extensive regions of unexplored composition space, the relatively small amount of data available, and considerable computational cost. Machine learning has inherent advantages over traditional modeling owing to its flexibility as new data becomes available and its rapid ability to construct relationships between input data and target outputs. Using a combination of CALPHAD and chemical attributes in a machine learning framework, we demonstrate the ability to augment DFT methodologies and predict the likelihood of successful synthesis for a given composition, thus allowing exploration of material space in an unconstrained manner; several specific examples are demonstrated.