DScribe: Library of descriptors for machine learning in materials science

DScribe is a software package for machine learning that provides popular feature transformations (“descriptors”) for atomistic materials simulations. DScribe accelerates the application of machine learning for atomistic property prediction by providing user-friendly, off-the-shelf descriptor impleme...

Full description

Saved in:
Bibliographic Details
Published in:Computer physics communications Vol. 247; p. 106949
Main Authors: Himanen, Lauri, Jäger, Marc O.J., Morooka, Eiaki V., Federici Canova, Filippo, Ranawat, Yashasvi S., Gao, David Z., Rinke, Patrick, Foster, Adam S.
Format: Journal Article
Language:English
Published: Elsevier B.V 01.02.2020
Subjects:
Descriptor
Machine learning
Materials science
Open source
Python
Materials science
Descriptor
Open source
Machine learning
Python
ISSN:0010-4655, 1879-2944
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:DScribe is a software package for machine learning that provides popular feature transformations (“descriptors”) for atomistic materials simulations. DScribe accelerates the application of machine learning for atomistic property prediction by providing user-friendly, off-the-shelf descriptor implementations. The package currently contains implementations for Coulomb matrix, Ewald sum matrix, sine matrix, Many-body Tensor Representation (MBTR), Atom-centered Symmetry Function (ACSF) and Smooth Overlap of Atomic Positions (SOAP). Usage of the package is illustrated for two different applications: formation energy prediction for solids and ionic charge prediction for atoms in organic molecules. The package is freely available under the open-source Apache License 2.0. Program Title: DScribe Program Files doi:http://dx.doi.org/10.17632/vzrs8n8pk6.1 Licensing provisions: Apache-2.0 Programming language: Python/C/C++ Supplementary material: Supplementary Information as PDF Nature of problem: The application of machine learning for materials science is hindered by the lack of consistent software implementations for feature transformations. These feature transformations, also called descriptors, are a key step in building machine learning models for property prediction in materials science. Solution method: We have developed a library for creating common descriptors used in machine learning applied to materials science. We provide an implementation the following descriptors: Coulomb matrix, Ewald sum matrix, sine matrix, Many-body Tensor Representation (MBTR), Atom-centered Symmetry Functions (ACSF) and Smooth Overlap of Atomic Positions (SOAP). The library has a python interface with computationally intensive routines written in C or C++. The source code, tutorials and documentation are provided online. A continuous integration mechanism is set up to automatically run a series of regression tests and check code coverage when the codebase is updated.
ISSN:0010-4655
1879-2944
DOI:10.1016/j.cpc.2019.106949