Fast predictions of lattice energies by continuous isometry invariants of crystal structures

Ropers, Jakob, Mosca, Marco M ORCID: 0000-0002-1764-2814, Anosova, Olga, Kurlin, Vitaliy ORCID: 0000-0001-5328-5351 and Cooper, Andrew I (2021) Fast predictions of lattice energies by continuous isometry invariants of crystal structures. [Preprint]

Text energy_predictions.pdf - Author Accepted Manuscript Download (1MB) | Preview

Abstract

Crystal Structure Prediction (CSP) aims to discover solid crystalline materials by optimizing periodic arrangements of atoms, ions or molecules. CSP takes weeks of supercomputer time because of slow energy minimizations for millions of simulated crystals. The lattice energy is a key physical property, which determines thermodynamic stability of a crystal but has no simple analytic expression. Past machine learning approaches to predict the lattice energy used slow crystal descriptors depending on manually chosen parameters. The new area of Periodic Geometry offers much faster isometry invariants that are also continuous under perturbations of atoms. Our experiments on simulated crystals confirm that a small distance between the new invariants guarantees a small difference of energies. We compare several kernel methods for invariant-based predictions of energy and achieve the mean absolute error of less than 5kJ/mole or 0.05eV/atom on a dataset of 5679 crystals.

Item Type:	Preprint
Additional Information:	To appear in the proceedings of DACOMSIN (Data and Computation for Materials Science and Innovation) 2021, https://en.misis.ru/university/colleges/sound/thermochemistry/dacomsin/
Uncontrolled Keywords:	cond-mat.mtrl-sci, cond-mat.mtrl-sci, cs.CE, cs.LG
Divisions:	Faculty of Health and Life Sciences Faculty of Health and Life Sciences > Institute of Population Health Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	06 Oct 2021 14:18
Last Modified:	14 Mar 2024 17:32
DOI:	10.48550/arxiv.2108.07233
Related URLs:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3139490