高技术通讯2025，Vol.35Issue(11)：1174-1187,14.DOI:10.3772/j.issn.1002-0470.2025.11.003
深度神经网络驱动的第一性原理精度分子动力学的研究进展
Survey on deep neural network-driven ab initio molecular dynamics
摘要
Abstract
Neural network force fields(NNFFs)have become a new paradigm in molecular dynamics(MD)simulations.This paper distinguishes NNFF models by their descriptors(fixed or learnable),classifies them into fixed descrip-tor neural network force fields and learnable descriptor neural network force fields.This paper introduces some rep-resentative NNFF models.We select two representative methods,the two-body Gaussian basis set and the deep po-tential model respectively,and further analyzes their design guidelines and principles.This paper also explores the characteristics of different types of NNFFs and tests them on four real datasets to evaluate different types of NNFF models.关键词
分子动力学/神经网络力场/描述符Key words
molecular dynamic/neural network force field/descriptor引用本文复制引用
HU Siyu,LI Jimei,JIA Weile,TAN Guangming..深度神经网络驱动的第一性原理精度分子动力学的研究进展[J].高技术通讯,2025,35(11):1174-1187,14.基金项目
国家自然科学基金重点(62032023)资助项目. （62032023）
