The University of Southampton
University of Southampton Institutional Repository

Multi-fidelity statistical machine learning for molecular crystal structure prediction

Multi-fidelity statistical machine learning for molecular crystal structure prediction
Multi-fidelity statistical machine learning for molecular crystal structure prediction

The prediction of crystal structures from first-principles requires highly accurate energies for large numbers of putative crystal structures. High accuracy of solid state density functional theory (DFT) calculations is often required, but hundreds or more structures can be present in the low energy region of interest, so that the associated computational costs are prohibitive. Here, we apply statistical machine learning to predict expensive hybrid functional DFT (PBE0) calculations using a multifidelity approach to re-evaluate the energies of crystal structures predicted with an inexpensive force field. The method uses an autoregressive Gaussian process, making use of less expensive GGA DFT (PBE) calculations to bridge the gap between the force field and PBE0 energies. The method is benchmarked on the crystal structure landscapes of three small, hydrogen-bonded organic molecules and shown to produce accurate predictions of energies and crystal structure ranking using small numbers of the most expensive calculations; the PBE0 energies can be predicted with errors of less than 1 kJ mol-1 with between 4.2 and 6.8% of the cost of the full calculations. As the model that we have developed is probabilistic, we discuss how the uncertainties in predicted energies impact the assessment of the energetic ranking of crystal structures.

computational chemistry, crystal structure prediction, machine learning, statistical learning
1089-5639
8065-8078
Egorova, Olga
49e91576-5a13-476b-8dbd-6091d82ce907
Hafizi, Roohollah
bdf707e3-cfc0-4c9b-8daa-d1acc5123632
Woods, David
ae21f7e2-29d9-4f55-98a2-639c5e44c79c
Day, Graeme M.
e3be79ba-ad12-4461-b735-74d5c4355636
Egorova, Olga
49e91576-5a13-476b-8dbd-6091d82ce907
Hafizi, Roohollah
bdf707e3-cfc0-4c9b-8daa-d1acc5123632
Woods, David
ae21f7e2-29d9-4f55-98a2-639c5e44c79c
Day, Graeme M.
e3be79ba-ad12-4461-b735-74d5c4355636

Egorova, Olga, Hafizi, Roohollah, Woods, David and Day, Graeme M. (2020) Multi-fidelity statistical machine learning for molecular crystal structure prediction. Journal of Physical Chemistry A, 124 (39), 8065-8078. (doi:10.1021/acs.jpca.0c05006).

Record type: Article

Abstract

The prediction of crystal structures from first-principles requires highly accurate energies for large numbers of putative crystal structures. High accuracy of solid state density functional theory (DFT) calculations is often required, but hundreds or more structures can be present in the low energy region of interest, so that the associated computational costs are prohibitive. Here, we apply statistical machine learning to predict expensive hybrid functional DFT (PBE0) calculations using a multifidelity approach to re-evaluate the energies of crystal structures predicted with an inexpensive force field. The method uses an autoregressive Gaussian process, making use of less expensive GGA DFT (PBE) calculations to bridge the gap between the force field and PBE0 energies. The method is benchmarked on the crystal structure landscapes of three small, hydrogen-bonded organic molecules and shown to produce accurate predictions of energies and crystal structure ranking using small numbers of the most expensive calculations; the PBE0 energies can be predicted with errors of less than 1 kJ mol-1 with between 4.2 and 6.8% of the cost of the full calculations. As the model that we have developed is probabilistic, we discuss how the uncertainties in predicted energies impact the assessment of the energetic ranking of crystal structures.

Text
multifidelity_modelling_CSP_revision - Accepted Manuscript
Download (1MB)
Text
Supporting information
Restricted to Repository staff only
Request a copy

More information

Accepted/In Press date: 3 September 2020
e-pub ahead of print date: 3 September 2020
Published date: 1 October 2020
Additional Information: Funding Information: We thank the EPSRC for funding, via Grant EP/S015418/1. We acknowledge the use of the IRIDIS High Performance Computing Facility and associated support services at the University of Southampton in the completion of this work. We are also grateful to the U.K. Materials and Molecular Modelling Hub for computational resources, which is partially funded by the EPSRC (EP/P020194/1). We thank David McDonagh for sharing his experiences during the first stages of the project. R.H. thanks Barry Searle for his helpful advice on convergence of crystal17 calculations. Publisher Copyright: © 2020 American Chemical Society.
Keywords: computational chemistry, crystal structure prediction, machine learning, statistical learning

Identifiers

Local EPrints ID: 443809
URI: http://eprints.soton.ac.uk/id/eprint/443809
ISSN: 1089-5639
PURE UUID: 94c2b526-f649-4f18-9de5-dd5de3861d32
ORCID for Roohollah Hafizi: ORCID iD orcid.org/0000-0001-6513-4446
ORCID for David Woods: ORCID iD orcid.org/0000-0001-7648-429X
ORCID for Graeme M. Day: ORCID iD orcid.org/0000-0001-8396-2771

Catalogue record

Date deposited: 14 Sep 2020 16:31
Last modified: 17 Mar 2024 05:52

Export record

Altmetrics

Contributors

Author: Olga Egorova
Author: Roohollah Hafizi ORCID iD
Author: David Woods ORCID iD
Author: Graeme M. Day ORCID iD

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 http://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.

×