Department of Mechanical Engineering and Applied Mechanics, University of Pennsylvania, Philadelphia, Pennsylvania 19104, USA.
J Chem Phys. 2022 May 14;156(18):184114. doi: 10.1063/5.0083198.
A neural network-assisted molecular dynamics method is developed to reduce the computational cost of open boundary simulations. Particle influxes and neural network-derived forces are applied at the boundaries of an open domain consisting of explicitly modeled Lennard-Jones atoms in order to represent the effects of the unmodeled surrounding fluid. Canonical ensemble simulations with periodic boundaries are used to train the neural network and to sample boundary fluxes. The method, as implemented in the LAMMPS, yields temperature, kinetic energy, potential energy, and pressure values within 2.5% of those calculated using periodic molecular dynamics and runs two orders of magnitude faster than a comparable grand canonical molecular dynamics system.
我们开发了一种基于神经网络的分子动力学方法，以降低开边界模拟的计算成本。在由显式建模的 Lennard-Jones 原子组成的开域边界施加粒子流入和神经网络衍生的力，以表示未建模的周围流体的影响。使用具有周期性边界的正则系综模拟来训练神经网络并采样边界通量。该方法在 LAMMPS 中的实现，使温度、动能、位能和压力值与使用周期性分子动力学计算的值相差在 2.5%以内，并且比可比的巨正则分子动力学系统快两个数量级。
