Updates to the DScribe library : New descriptors and derivatives

We present an update of the DScribe package, a Python library for atomistic descriptors. The update extends DScribe’s descriptor selection with the Valle-Oganov materials fingerprint and provides descriptor derivatives to enable more advanced machine learning tasks, such as force prediction and structure optimization. For all descriptors, numeric derivatives are now available in DScribe. For the many-body tensor representation (MBTR) and the Smooth Overlap of Atomic Positions (SOAP), we have also implemented analytic derivatives. We demonstrate the effectiveness of the descriptor derivatives for machine learning models of Cu clusters and perovskite alloys.

Description

Funding Information: We acknowledge the funding from the European Union’s Horizon program under Grant Agreement No. 951786, the Academy of Finland through Project No. 334532, and the Center of Excellence Virtual Laboratory for Molecular Level Atmospheric Transformations (VILMA; Project No. 346377). We further acknowledge the CSC-IT Center for Science, Finland, and the Aalto Science-IT project. | openaire: EC/H2020/951786/EU//NOMAD CoE

DOI

10.1063/5.0151031

Citation

Laakso, J, Himanen, L, Homm, H, Morooka, E V, Jäger, M O J, Todorović, M & Rinke, P 2023, ' Updates to the DScribe library : New descriptors and derivatives ', Journal of Chemical Physics, vol. 158, no. 23, 234802, pp. 1-8 . https://doi.org/10.1063/5.0151031

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202406204631

Collections

[article-cris] Perustieteiden korkeakoulu / SCI

Show all metadata

Updates to the DScribe library : New descriptors and derivatives

Access rights

URL

Journal Title

Journal ISSN

Volume Title

Authors

Date

Department

Major/Subject

Mcode

Degree programme

Language

Pages

Series

Abstract

Description

Keywords

Other note

DOI

Citation

Permanent link to this item

Collections