arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.04009cond-mat.mtrl-sci
收藏

用于机器学习潜力的系统化原子结构数据集:在镁缺陷中的应用

Systematic Atomic Structure Datasets for Machine Learning Potentials: Application to Defects in Magnesium

Marvin Poul, Liam Huber, Erik Bitzek, Jörg Neugebauer

摘要:

我们提出了一个物理动机的策略,用于构建可转移机器学习原子间势的训练集。它基于对随机晶体结构中所有可能的空间群的系统探索,以及细胞形状,大小和原子位置的变形。由此产生的潜力原来是无偏的,一般适用于散装缺陷的研究,而不包括任何缺陷结构的训练集或采用任何额外的主动学习。使用这种方法,我们构建了纯镁,再现六方密堆积(hcp)和体心立方(bcc)多晶型物的属性很好的可转移的潜力。在这个过程中,我们研究了不同类型的训练结构如何影响所产生的潜力的属性和预测能力。

英文摘要:

We present a physically motivated strategy for the construction of training sets for transferable machine learning interatomic potentials. It is based on a systematic exploration of all possible space groups in random crystal structures, together with deformations of cell shape, size, and atomic positions. The resulting potentials turn out to be unbiased and generically applicable to studies of bulk defects without including any defect structures in the training set or employing any additional Active Learning. Using this approach we construct transferable potentials for pure Magnesium that reproduce the properties of hexagonal closed packed (hcp) and body centered cubic (bcc) polymorphs very well. In the process we investigate how different types of training structures impact the properties and the predictive power of the resulting potential.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑