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 2110.00624cond-mat.mtrl-sciphysics.comp-ph
收藏

超快可解释机器学习势

Ultra-fast interpretable machine-learning potentials

Stephen R. Xie, Matthias Rupp, Richard G. Hennig

AI总结:

本文提出结合B样条基与正则化线性回归的可解释机器学习势,兼具物理可解释性、精度与超高速,比最先进机器学习势快2-4个数量级,可精确恢复经验势并准确预测DFT性质。

摘要:

全原子动力学模拟是物理学、化学和材料科学中不可或缺的定量工具,但由于计算效率与预测精度之间的权衡,大规模系统和长时间模拟仍然具有挑战性。为应对这一挑战,我们将有效的二体和三体势与三次B样条基函数相结合,并采用正则化线性回归,从而获得机器学习势,这些势在物理上可解释,对应用足够精确,速度与最快的传统经验势相当,并且比最先进的机器学习势快两到四个数量级。对于来自经验势的数据,我们展示了势的精确恢复。对于来自密度泛函理论的数据,预测的能量、力以及衍生性质(包括声子谱、弹性常数和熔点)与参考方法的结果紧密匹配。所引入的势可能有助于在长时间尺度上对大型原子系统进行准确的全原子动力学模拟。

英文摘要:

All-atom dynamics simulations are an indispensable quantitative tool in physics, chemistry, and materials science, but large systems and long simulation times remain challenging due to the trade-off between computational efficiency and predictive accuracy. To address this challenge, we combine effective two- and three-body potentials in a cubic B-spline basis with regularized linear regression to obtain machine-learning potentials that are physically interpretable, sufficiently accurate for applications, as fast as the fastest traditional empirical potentials, and two to four orders of magnitude faster than state-of-the-art machine-learning potentials. For data from empirical potentials, we demonstrate exact retrieval of the potential. For data from density functional theory, the predicted energies, forces, and derived properties, including phonon spectra, elastic constants, and melting points, closely match those of the reference method. The introduced potentials might contribute towards accurate all-atom dynamics simulations of large atomistic systems over long time scales.

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。

↑