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.
Updates to the DScribe library: New descriptors and derivatives
Note: This paper is part of the JCP Special Topic on Software for Atomistic Machine Learning.
Jarno Laakso, Lauri Himanen, Henrietta Homm, Eiaki V. Morooka, Marc O. J. Jäger, Milica Todorović, Patrick Rinke; Updates to the DScribe library: New descriptors and derivatives. J. Chem. Phys. 21 June 2023; 158 (23): 234802. https://doi.org/10.1063/5.0151031
Download citation file: