Department of Chemistry, Chicago Center for Theoretical Chemistry, James Franck Institute, and Institute for Biophysical Dynamics, The University of Chicago, Chicago, Illinois 60637, United States.
J Chem Theory Comput. 2022 Oct 11;18(10):5856-5863. doi: 10.1021/acs.jctc.2c00706. Epub 2022 Sep 14.
For nearly the past 30 years, centroid molecular dynamics (CMD) has proven to be a viable classical-like phase space formulation for the calculation of quantum dynamical properties. However, calculation of the centroid effective force remains a significant computational cost and limits the ability of CMD to be an efficient approach to study condensed phase quantum dynamics. In this paper, we introduce a neural network-based methodology for first learning the centroid effective force from path integral molecular dynamics data, which is subsequently used as an effective force field to evolve the centroids directly with the CMD algorithm. This method, called machine-learned centroid molecular dynamics (ML-CMD), is faster and far less costly than both standard "on the fly" CMD and ring polymer molecular dynamics (RPMD). The training aspect of ML-CMD is also straightforwardly implemented utilizing the DeepMD software kit. ML-CMD is then applied to two model systems to illustrate the approach: liquid para-hydrogen and water. The results show comparable accuracy to both CMD and RPMD in the estimation of quantum dynamical properties, including the self-diffusion constant and velocity time correlation function, but with significantly reduced overall computational cost.
近 30 年来，质心分子动力学（CMD）已被证明是一种可行的经典类相空间表述，可用于计算量子动力学性质。然而，质心有效力的计算仍然是一个巨大的计算成本，限制了 CMD 作为一种有效方法来研究凝聚相量子动力学的能力。在本文中，我们引入了一种基于神经网络的方法，首先从路径积分分子动力学数据中学习质心有效力，然后将其用作有效力场，直接使用 CMD 算法演化质心。这种方法称为基于机器学习的质心分子动力学（ML-CMD），比标准的“即时”CMD 和环聚合物分子动力学（RPMD）更快，成本也低得多。ML-CMD 的训练方面也可以利用 DeepMD 软件包直接实现。然后，我们将 ML-CMD 应用于两个模型系统，以说明该方法：液氢和水。结果表明，在估计量子动力学性质方面，包括自扩散常数和速度时间相关函数，ML-CMD 与 CMD 和 RPMD 的准确性相当，但总体计算成本显著降低。
