文献类型：期刊文献

英文题名：Molecular Dynamics Simulations of Molten Magnesium Chloride Using Machine-Learning-Based Deep Potential

作者：Liang, Wenshuo[1,2];Lu, Guimin[1,2];Yu, Jianguo[1,2]

机构：[1]East China Univ Sci & Technol, Sch Resources & Environm Engn, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Natl Engn Res Ctr Integrated Utilizat Salt Lake R, Shanghai 200237, Peoples R China

年份：2020

卷号：3

期号：12

外文期刊名：ADVANCED THEORY AND SIMULATIONS

收录：;EI(收录号：20204409442961);WOS:【SCI-EXPANDED(收录号:WOS:000586457200001)】；

基金：The authors acknowledge the financial support provided by the National Natural Science Foundation of China (Grant Nos. U1407202 and U1407126).

语种：英文

外文关键词：deep potentials; machine learning; magnesium chloride; molecular dynamics simulations

摘要：In previous work, molten magnesium chloride has been investigated using first-principles molecular dynamics (FPMD) simulations based on density functional theory (DFT). However, such simulations are computationally intensive and therefore are restricted in terms of simulated size and time. In this work, a machine learning-based deep potential (DP) is trained to accelerate the molecular dynamics simulation of molten magnesium chloride. The trained DP can accurately describe the energies and forces with the prediction errors in energy and force being 1.76 x 10(-3) eV/atom and 4.76 x 10(-2) eV angstrom(-1), respectively. Applying the deep potential molecular dynamics (DPMD) approach, simulations can be performed with more than 1000 atoms, which is infeasible for FPMD simulations. Additionally, the partial radial distribution functions, angle distribution functions, densities, and self-diffusion coefficients predicted by DPMD simulations are also in reasonable agreement with FPMD or experimental results. This work shows that the DP enables higher efficiency and similar accuracy relative to DFT, exhibiting a bright application prospect in modeling molten salt systems.