Department of Applied Physics, Aalto University, P.O. Box 11100, 00076 Aalto, Finland.
Department of Mechanical and Materials Engineering, University of Turku, FI-20014 Turku, Finland.
J Chem Phys. 2023 Jun 21;158(23). doi: 10.1063/5.0151031.
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.
我们介绍了 DScribe 包的更新，这是一个用于原子描述符的 Python 库。此次更新扩展了 DScribe 的描述符选择功能，增加了 Valle-Oganov 材料指纹，并提供了描述符导数，以支持更高级的机器学习任务，如力预测和结构优化。现在，DScribe 中所有描述符都可以提供数值导数。对于多体张量表示 (MBTR) 和原子位置平滑重叠 (SOAP)，我们还实现了解析导数。我们演示了描述符导数在 Cu 团簇和钙钛矿合金的机器学习模型中的有效性。
