Inferring energy-composition relationships with Bayesian optimization enhances exploration of inorganic materials

TL;DR

This paper introduces a Bayesian optimization method called PhaseBO that efficiently explores inorganic material compositions, improving discovery rates without sacrificing energy evaluation accuracy.

Contribution

It presents a novel sampling approach that enhances exploration of compositional space, accelerating material discovery with accurate energy predictions.

Findings

PhaseBO improves exploration efficiency

Accelerates discovery of new materials

Maintains high accuracy in energy evaluation

Abstract

Computational exploration of the compositional spaces of materials can provide guidance for synthetic research and thus accelerate the discovery of novel materials. Most approaches employ high-throughput sampling and focus on reducing the time for energy evaluation for individual compositions, often at the cost of accuracy. Here, we present an alternative approach focusing on effective sampling of the compositional space. The learning algorithm PhaseBO optimizes the stoichiometry of the potential target material while improving the probability of and accelerating its discovery without compromising the accuracy of energy evaluation.