How to represent crystal structures for machine learning: Towards fast prediction of electronic properties

K. T. Schütt, H. Glawe, F. Brockherde, A. Sanna, K. R. Müller, E. K.U. Gross

Research output: Contribution to journalArticlepeer-review

350 Scopus citations

Abstract

High-throughput density functional calculations of solids are highly time-consuming. As an alternative, we propose a machine learning approach for the fast prediction of solid-state properties. To achieve this, local spin-density approximation calculations are used as a training set. We focus on predicting the value of the density of electronic states at the Fermi energy. We find that conventional representations of the input data, such as the Coulomb matrix, are not suitable for the training of learning machines in the case of periodic solids. We propose a novel crystal structure representation for which learning and competitive prediction accuracies become possible within an unrestricted class of spd systems of arbitrary unit-cell size.

Original languageAmerican English
Article number205118
JournalPhysical Review B - Condensed Matter and Materials Physics
Volume89
Issue number20
DOIs
StatePublished - 21 May 2014
Externally publishedYes

Fingerprint

Dive into the research topics of 'How to represent crystal structures for machine learning: Towards fast prediction of electronic properties'. Together they form a unique fingerprint.

Cite this