2026-10-14T13:03:54Z https://data.mendeley.com/oai

oai:data.mendeley.com/vzrs8n8pk6.1 2019-10-02T13:27:48Z

Ballantyne, John DScribe: Library of descriptors for machine learning in materials science Mendeley Data 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. Computational Physics Himanen, Lauri Jäger, Marc O.J. Morooka, Eiaki V. Canova, Filippo Federici Ranawat, Yashasvi S. Gao, David Z. Rinke, Patrick Foster, Adam S. Dataset doi:10.17632/vzrs8n8pk6.1 oai:data.mendeley.com/vzrs8n8pk6.1 Apache License 2.0 http://www.apache.org/licenses/LICENSE-2.0 https://data.mendeley.com/datasets/vzrs8n8pk6 2019-10-02T13:27:48Z