A physics-informed feature engineering approach to use machine learning with limited amounts of data for alloy design: shape memory alloy demonstration

Machine learning using limited data from physical experiments is shown to work to predict new shape memory alloys in a high dimensional alloy design space that considers chemistry and thermal post-processing. The key to enabling the machine learning algorithms to make predictions of new alloys and their post-processing is shown to be a physics-informed featured engineering approach. Specifically, elemental features previously engineered by the computational materials community to model composition effects in materials are combined with newly engineered heat treatment features. These new features result from pre-processing the heat treatment data using mathematical relationships known to describe the thermodynamics and kinetics of precipitation in alloys. The prior application of the nonlinear physical models to the data in effect linearizes some of the complex alloy development trends a priori using known physics, and results in greatly improved performance of the ML algorithms trained on relatively few data points.