Autonomous Efficient Experiment Design for Materials Discovery with Bayesian Model Averaging

TL;DR

This paper introduces an autonomous experiment design framework that combines Bayesian Model Averaging with Bayesian Optimization to efficiently explore materials space under resource constraints, demonstrated on MAX ternary carbides/nitrides.

Contribution

It advances materials discovery by integrating model uncertainty into resource-aware experimental design using Bayesian methods.

Findings

Efficient exploration of MAX ternary carbide/nitride space.

Incorporates model uncertainty into experiment planning.

Demonstrates autonomous, adaptive learning in materials discovery.

Abstract

The accelerated exploration of the materials space in order to identify configurations with optimal properties is an ongoing challenge. Current paradigms are typically centered around the idea of performing this exploration through high-throughput experimentation/computation. Such approaches, however, do not account fo the always present constraints in resources available. Recently, this problem has been addressed by framing materials discovery as an optimal experiment design. This work augments earlier efforts by putting forward a framework that efficiently explores the materials design space not only accounting for resource constraints but also incorporating the notion of model uncertainty. The resulting approach combines Bayesian Model Averaging within Bayesian Optimization in order to realize a system capable of autonomously and adaptively learning not only the most promising regions in the materials space but also the models that most efficiently guide such exploration. The framework is demonstrated by efficiently exploring the MAX ternary carbide/nitride space through Density Functional Theory (DFT) calculations.