arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.02741cond-mat.mtrl-sci
收藏

机器学习原子间势高精度的概念和实践基础

Conceptual and practical bases for the high accuracy of machine learning interatomic potential

Akira Takahashi, Atsuto Seko, Isao Tanaka

摘要:

基于密度泛函理论(DFT)计算获得的大数据集的机器学习原子间相互作用势(MLIPs)最近得到了发展。这项研究为MLIPs的高精度提供了概念和实践基础,尽管MLIPs一直被认为只是原子能的精确黑箱描述。我们还构建了最准确的MLIP的元素Ti以往报道使用线性MLIP框架和许多角度依赖的描述符,这也对应于一个概括的修改嵌入原子方法(MEAM)的潜力。

英文摘要:

Machine learning interatomic potentials (MLIPs) based on a large dataset obtained by density functional theory (DFT) calculation have been developed recently. This study gives both conceptual and practical bases for the high accuracy of MLIPs, although MLIPs have been considered to be simply an accurate black-box description of atomic energy. We also construct the most accurate MLIP of the elemental Ti ever reported using a linearized MLIP framework and many angular-dependent descriptors, which also corresponds to a generalization of the modified embedded atom method (MEAM) 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。

↑