Bayesian optimization of high entropy alloy properties

High entropy alloys, or better termed as multi-principal element solid solution alloys (MPEA), represent a class of
materials with promising mechanical properties. The large combinatorial variety of compositions, the complex alloy structure and magnetic state make them hard to study using conventional first-principle methods.
In this work, we present a computationally efficient high-throughput workflow based on
ab initio calculations within the coherent potential approximation. To make the methodology predictive, we
apply an exchange-correlation correction to the equation of state and take into account thermal effects
on the magnetic state and the equilibrium volume. The approach shows good agreement with available experimental
data on bulk properties of solid solutions. The workflow is applied to a variety of
iron-group MPEA to investigate their solid solution strengthening within a model based on the effective
medium representation of an alloy. Finally, we incorporate the workflow into a Bayesian optimization framework
to demonstrate the potential of such an approach for computationally efficient materials design.