Collaboratory for Advanced Computing and Simulations, University of Southern California, Los Angeles, California 90089, United States.
Center for Integrated Nanotechnologies, Sandia National Laboratory, Albuquerque, New Mexico 87185, United States.
J Chem Inf Model. 2022 Jul 25;62(14):3346-3351. doi: 10.1021/acs.jcim.2c00515. Epub 2022 Jul 5.
The principle of least action is the cornerstone of classical mechanics, theory of relativity, quantum mechanics, and thermodynamics. Here, we describe how a neural network (NN) learns to find the trajectory for a Lennard-Jones (LJ) system that maintains balance in minimizing the Onsager-Machlup (OM) action and maintaining the energy conservation. The phase-space trajectory thus calculated is in excellent agreement with the corresponding results from the "ground-truth" molecular dynamics (MD) simulation. Furthermore, we show that the NN can easily find structural transformation pathways for LJ clusters, for example, the basin-hopping transformation of an LJ from an incomplete Mackay icosahedron to a truncated face-centered cubic octahedron. Unlike MD, the NN computes atomic trajectories over the entire temporal domain in one fell swoop, and the NN time step is a factor of 20 larger than the MD time step. The NN approach to OM action is quite general and can be adapted to model morphometrics in a variety of applications.
最小作用量原理是经典力学、相对论、量子力学和热力学的基石。在这里，我们描述了神经网络（NN）如何学习为 Lennard-Jones（LJ）系统找到保持平衡的轨迹，以最小化 Onsager-Machlup（OM）作用并保持能量守恒。由此计算出的相空间轨迹与“真实”分子动力学（MD）模拟的相应结果非常吻合。此外，我们还表明，神经网络可以轻松找到 LJ 团簇的结构转变途径，例如，LJ 从不完全 Mackay 二十面体到截断面心立方八面体的盆地跳跃转变。与 MD 不同，NN 可以在一次计算中一次性计算整个时间域内的原子轨迹，并且 NN 的时间步长是 MD 时间步长的 20 倍。NN 对 OM 作用的方法非常通用，可以适应各种应用中的形态计量学建模。
