Bayesian Optimization in Materials Science: A Survey

TL;DR

This survey reviews how Bayesian optimization techniques are applied in materials science to efficiently explore large design spaces and optimize material properties, aiming to foster collaboration between AI and materials communities.

Contribution

It provides a comprehensive overview of Bayesian optimization methods in materials science, highlighting challenges and opportunities for interdisciplinary research.

Findings

Bayesian optimization effectively reduces experimental costs in materials design.

There is minimal overlap between AI and materials science communities on Bayesian methods.

The survey identifies key challenges and future research directions.

Abstract

Bayesian optimization is used in many areas of AI for the optimization of black-box processes and has achieved impressive improvements of the state of the art for a lot of applications. It intelligently explores large and complex design spaces while minimizing the number of evaluations of the expensive underlying process to be optimized. Materials science considers the problem of optimizing materials' properties given a large design space that defines how to synthesize or process them, with evaluations requiring expensive experiments or simulations -- a very similar setting. While Bayesian optimization is also a popular approach to tackle such problems, there is almost no overlap between the two communities that are investigating the same concepts. We present a survey of Bayesian optimization approaches in materials science to increase cross-fertilization and avoid duplication of work. We highlight common challenges and opportunities for joint research efforts.