The University of Southampton
University of Southampton Institutional Repository

Machine-learnt fragment-based energies for crystal structure prediction

Machine-learnt fragment-based energies for crystal structure prediction
Machine-learnt fragment-based energies for crystal structure prediction
Crystal structure prediction involves a search of a complex configurational space for local minima corresponding to stable crystal structures, which can be performed efficiently using atom-atom force fields for the assessment of intermolecular interactions. However, for challenging systems, the limitations in the accuracy of force fields prevents a reliable assessment of the relative thermodynamic stability of potential structures, while the cost of fully quantum mechanical approaches can limit applications of the methods. We present a method to rapidly improve force field lattice energies by correcting two-body interactions with a higher level of theory in a fragment-based approach, and predicting these corrections with machine learning. Corrected lattice energies with commonly used density functionals and second order perturbation theory (MP2) all significantly improve the ranking of experimentally known polymorphs where the rigid molecule model is applicable. The relative lattice energies of known polymorphs are also found to systematically improve with the fragment corrections. Predicting two-body interactions with atom-centered symmetry functions in a Gaussian process is found to give highly accurate results using as little as 10-20% of the data for training, reducing the cost of the energy correction by up to an order of magnitude. The machine learning approach opens up the possibility of more widespread use of fragment-based methods in crystal structure prediction, whose increased accuracy at a low computational cost will benefit applications in areas such as polymorph screening and computer-guided materials discovery.
machine learning (artificial intelligence), crystal structure prediction, polymorphism, Crystal engineering
1549-9618
McDonagh, David
1ff4dd30-614e-484e-91b9-eef7002377a9
Skylaris, Chris-Kriton
8f593d13-3ace-4558-ba08-04e48211af61
Day, Graeme M.
e3be79ba-ad12-4461-b735-74d5c4355636
McDonagh, David
1ff4dd30-614e-484e-91b9-eef7002377a9
Skylaris, Chris-Kriton
8f593d13-3ace-4558-ba08-04e48211af61
Day, Graeme M.
e3be79ba-ad12-4461-b735-74d5c4355636

McDonagh, David, Skylaris, Chris-Kriton and Day, Graeme M. (2019) Machine-learnt fragment-based energies for crystal structure prediction. Journal of Chemical Theory and Computation. (doi:10.1021/acs.jctc.9b00038).

Record type: Article

Abstract

Crystal structure prediction involves a search of a complex configurational space for local minima corresponding to stable crystal structures, which can be performed efficiently using atom-atom force fields for the assessment of intermolecular interactions. However, for challenging systems, the limitations in the accuracy of force fields prevents a reliable assessment of the relative thermodynamic stability of potential structures, while the cost of fully quantum mechanical approaches can limit applications of the methods. We present a method to rapidly improve force field lattice energies by correcting two-body interactions with a higher level of theory in a fragment-based approach, and predicting these corrections with machine learning. Corrected lattice energies with commonly used density functionals and second order perturbation theory (MP2) all significantly improve the ranking of experimentally known polymorphs where the rigid molecule model is applicable. The relative lattice energies of known polymorphs are also found to systematically improve with the fragment corrections. Predicting two-body interactions with atom-centered symmetry functions in a Gaussian process is found to give highly accurate results using as little as 10-20% of the data for training, reducing the cost of the energy correction by up to an order of magnitude. The machine learning approach opens up the possibility of more widespread use of fragment-based methods in crystal structure prediction, whose increased accuracy at a low computational cost will benefit applications in areas such as polymorph screening and computer-guided materials discovery.

Text
A_Fragment_Based_Approach_to_Improving_Lattice_Energies_In_Crystal_Structure_Prediction_Using_Machine_Learning - Accepted Manuscript
Restricted to Repository staff only until 28 February 2020.
Request a copy
Text
SI_A_Fragment_Based_Approach_to_Improving_Lattice_Energies_In_Crystal_Structure_Prediction_Using_Machine_Learning
Restricted to Repository staff only until 28 February 2020.
Request a copy

More information

Accepted/In Press date: 28 February 2019
e-pub ahead of print date: 28 February 2019
Keywords: machine learning (artificial intelligence), crystal structure prediction, polymorphism, Crystal engineering

Identifiers

Local EPrints ID: 428828
URI: https://eprints.soton.ac.uk/id/eprint/428828
ISSN: 1549-9618
PURE UUID: 48b519ad-ae53-4886-b818-c9a991f9360f
ORCID for Chris-Kriton Skylaris: ORCID iD orcid.org/0000-0003-0258-3433
ORCID for Graeme M. Day: ORCID iD orcid.org/0000-0001-8396-2771

Catalogue record

Date deposited: 11 Mar 2019 17:30
Last modified: 16 Apr 2019 00:34

Export record

Altmetrics

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of https://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×