Transfer-Learning-Based Coarse-Graining Method for Simple Fluids: Toward Deep Inverse Liquid-State Theory
Transfer-Learning-Based Coarse-Graining Method for Simple Fluids: Toward Deep Inverse Liquid-State Theory
复制标题
DOI：
10.1021/acs.jpclett.8b03872
复制
发表时间：
2019-03-21
影响因子：
5.7
通讯作者：
Aluru, Narayana R.
中科院分区：
文献类型：
--
作者：
Moradzadeh, Alireza;Aluru, Narayana R.
机器学习是一种很有吸引力的范例，可以绕过与开发和优化力场参数相关的困难。本文利用深度神经网络(DNN)来研究液态理论的反问题，特别是得到了不同热力学状态下的径向分布函数(RDF)与Lennard-Jones(LJ)势参数之间的关系。利用分子动力学(MD)，一旦确定了原子间相互作用势，就可以确定许多可观测的量，包括RDF。然而，反问题(特定RDF的潜力的参数化)并不简单。本文提出了一种将离散神经网络与1.5TB MD轨迹大数据相结合的框架，对26000个不同系统的累积模拟时间为52亩S，用于预测LJ势参数。我们的结果表明，DNN不仅在原子LJ液体的参数化方面是成功的，而且对于简单多原子分子的粗粒模型的LJ势也是成功的。
Machine learning is an attractive paradigm to circumvent difficulties associated with the development and optimization of force-field parameters. In this study, a deep neural network (DNN) is used to study the inverse problem of the liquid-state theory, in particular, to obtain the relation between the radial distribution function (RDF) and the Lennard-Jones (LJ) potential parameters at various thermodynamic states. Using molecular dynamics (MD), many observables, including RDF, are determined once the interatomic potential is specified. However, the inverse problem (parametrization of the potential for a specific RDF) is not straightforward. Here we present a framework integrating DNN with big data from 1.5 TB of MD trajectories with a cumulative simulation time of 52 mu s for 26 000 distinct systems to predict LJ potential parameters. Our results show that DNN is successful not only in the parametrization of the atomic LJ liquids but also in parametrizing the LJ potential for coarse-grained models of simple multiatom molecules.