arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.14877cond-mat.mtrl-sci
收藏

多项式机器学习势对22种元素体系液态的预测能力

Predictive power of polynomial machine learning potentials for liquid states in 22 elemental systems

Kyoto University(京都大学)

Hayato Wakai, Atsuto Seko, Hirosato Izuta, Takayuki Nishiyama, Isao Tanaka

AI总结:

本文系统评估了多项式机器学习势在22种元素体系液态结构性质预测中的表现,发现其精度与DFT计算相当,验证了该方法对液态体系的广泛适用性。

摘要:

由多项式旋转不变量描述的多项式机器学习势(MLPs)已针对多种体系被系统地开发,并广泛应用于晶态中的多种场景。本研究系统考察了多项式MLPs对22种具有不同化学键合性质元素体系液态结构性质的预测能力,其中包括Si、Ge和Bi等表现出异常熔化行为的体系。我们比较了使用密度泛函理论(DFT)计算、多项式MLPs以及文献中其他原子间势进行分子动力学模拟所得到的液态结构性质。当前结果表明,多项式MLPs对液态结构性质一致地表现出高预测能力,其精度与典型DFT计算相当。

英文摘要:

The polynomial machine learning potentials (MLPs) described by polynomial rotational invariants have been systematically developed for various systems and used in diverse applications in crystalline states. In this study, we systematically investigate the predictive power of the polynomial MLPs for liquid structural properties in 22 elemental systems with diverse chemical bonding properties, including those showing anomalous melting behavior, such as Si, Ge, and Bi. We compare liquid structural properties obtained from molecular dynamics simulations using the density functional theory (DFT) calculation, the polynomial MLPs, and other interatomic potentials in the literature. The current results demonstrate that the polynomial MLPs consistently exhibit high predictive power for liquid structural properties with the same accuracy as that of typical DFT calculations.

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。

↑