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

20 December 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


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 two distinct classes of prediction; Performing crystal structure prediction via heuristic algorithms, using a range of established crystal structure prediction codes, and an emerging community using generative machine learning models to predict crystal structures directly. In this work, we demonstrate 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 to heuristic structure prediction results in both faster compute times per structure and leads to lower energies. This work provides to the community a set of eleven compounds with varying chemistry and complexity which can be used as a benchmark for new crystal structure prediction methods as they emerge.


Crystal structure prediction
Machine learning

Supplementary weblinks


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.