Multi-fidelity machine-learning with uncertainty quantification and Bayesian optimization for materials design: Application to ternary random alloys

TL;DR

This paper introduces a multi-fidelity Gaussian process framework combining DFT and interatomic potentials for efficient materials design, uncertainty quantification, and global optimization in ternary alloys.

Contribution

It is the first to apply multi-fidelity Gaussian processes to atomistic simulations, integrating DFT and classical potentials for materials discovery.

Findings

Successfully reproduces bulk modulus dependence across alloy compositions.

Demonstrates efficient on-the-fly optimization of alloy properties.

Provides uncertainty estimates for predictions in materials design.

Abstract

We present a scale-bridging approach based on a multi-fidelity (MF) machine-learning (ML) framework leveraging Gaussian processes (GP) to fuse atomistic computational model predictions across multiple levels of fidelity. Through the posterior variance of the MFGP, our framework naturally enables uncertainty quantification, providing estimates of confidence in the predictions. We used Density Functional Theory as high-fidelity prediction, while a ML interatomic potential is used as the low-fidelity prediction. Practical materials design efficiency is demonstrated by reproducing the ternary composition dependence of a quantity of interest (bulk modulus) across the full aluminum-niobium-titanium ternary random alloy composition space. The MFGP is then coupled to a Bayesian optimization procedure and the computational efficiency of this approach is demonstrated by performing an on-the-fly search for the global optimum of bulk modulus in the ternary composition space. The framework presented in this manuscript is the first application of MFGP to atomistic materials simulations fusing predictions between Density Functional Theory and classical interatomic potential calculations.