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

Vasylenko, Andrij ORCID: 0000-0002-6933-0628, Asher, Benjamin M, Collins, Christopher M ORCID: 0000-0002-0101-4426, Gaultois, Michael W ORCID: 0000-0003-2172-2507, Darling, George R ORCID: 0000-0001-9329-9993, Dyer, Matthew S ORCID: 0000-0002-4923-3003 and Rosseinsky, Matthew J ORCID: 0000-0002-1910-2483 (2024) Inferring energy-composition relationships with Bayesian optimization enhances exploration of inorganic materials JOURNAL OF CHEMICAL PHYSICS, 160 (5). 054110-. ISSN 0021-9606, 1089-7690

Access the full-text of this item by clicking on the Open Access link.

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.

Item Type:	Article
Uncontrolled Keywords:	34 Chemical Sciences, 7 Affordable and Clean Energy
Depositing User:	Symplectic Admin
Date Deposited:	05 Aug 2024 15:55
Last Modified:	16 Jun 2026 19:56
DOI:	10.1063/5.0180818
Open Access URL:	https://doi.org/10.1063/5.0180818
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3183355
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.