Integration of generative machine learning with the heuristic crystal structure prediction code FUSE

Collins, Christopher M ORCID: 0000-0002-0101-4426, Sayeed, Hasan M, Darling, George R ORCID: 0000-0001-9329-9993, Claridge, John B ORCID: 0000-0003-4849-6714, Sparks, Taylor D and Rosseinsky, Matthew J ORCID: 0000-0002-1910-2483 (2025) Integration of generative machine learning with the heuristic crystal structure prediction code FUSE FARADAY DISCUSSIONS, 256. pp. 85-103. ISSN 1359-6640, 1364-5498

PDF C_Collins_accepted.pdf - Author Accepted Manuscript Download (30MB) | Preview

Abstract

The prediction of new compounds via crystal structure prediction may transform how the materials chemistry community discovers new compounds. In the prediction of inorganic crystal structures there are three distinct classes of prediction: performing crystal structure prediction via heuristic algorithms, using a range of established crystal structure prediction codes, an emerging community using generative machine learning models to predict crystal structures directly and the use of mathematical optimisation to solve crystal structures exactly. In this work, we demonstrate the combination of heuristic and generative machine learning, the use of a generative machine learning model to produce the starting population of crystal structures for a heuristic algorithm and discuss the benefits, demonstrating the method on eight known compounds with reported crystal structures and three hypothetical compounds. We show that the integration of machine learning structure generation with heuristic structure prediction results in both faster compute times per structure and lower energies. This work provides to the community a set of eleven compounds with varying chemistry and complexity that can be used as a benchmark for new crystal structure prediction methods as they emerge.

Item Type:	Article
Uncontrolled Keywords:	3402 Inorganic Chemistry, 34 Chemical Sciences, Networking and Information Technology R&D (NITRD), Machine Learning and Artificial Intelligence, Generic health relevance
Depositing User:	Symplectic Admin
Date Deposited:	17 Sep 2024 07:36
Last Modified:	16 Jun 2026 20:14
DOI:	10.1039/d4fd00094c
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3184543
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.