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 DSribe. 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.
@article{arxiv.2303.14046,
title = {Updates to the DScribe Library: New Descriptors and Derivatives},
author = {Jarno Laakso and Lauri Himanen and Henrietta Homm and Eiaki V. Morooka and Marc O. J. Jäger and Milica Todorović and Patrick Rinke},
journal= {arXiv preprint arXiv:2303.14046},
year = {2023}
}
Comments
The following article has been submitted to The Journal of Chemical Physics. After it is published, it will be found at https://aip.scitation.org/toc/jcp/current