Neural network representation of electronic structure from ab initio molecular dynamics  

第一性原理分子动力学中电子结构的神经网络表达

作　　者：Qiangqiang Gu Linfeng Zhang Ji Feng 顾强强;张林峰;冯济(International Center for Quantum Materials,School of Physics,Peking University,Beijing 100871,China;Department of Mathematics and Program in Applied and Computational Mathematics,Princeton University,Princeton,NJ 08544,USA;Collaborative Innovation Center of Quantum Matter,Beijing 100871,China)

机构地区：[1]International Center for Quantum Materials,School of Physics,Peking University,Beijing 100871,China [2]Department of Mathematics and Program in Applied and Computational Mathematics,Princeton University,Princeton,NJ 08544,USA [3]Collaborative Innovation Center of Quantum Matter,Beijing 100871,China

出　　处：《Science Bulletin》2022年第1期29-37,M0003,共10页科学通报（英文版）

基　　金：supported by the National Natural Science Foundation of China(11725415 and 11934001);the Ministry of Science and Technology of China(2018YFA0305601 and2016YFA0301004);by the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB28000000);supported in part by the Center for Chemistry in Solution and at Interfaces(CSI)at Princeton University,funded by the DOE Award DE-SC0019394。

摘　　要：Despite their rich information content,electronic structure data amassed at high volumes in ab initio molecular dynamics simulations are generally under-utilized.We introduce a transferable high-fidelity neural network representation of such data in the form of tight-binding Hamiltonians for crystalline materials.This predictive representation of ab initio electronic structure,combined with machinelearning boosted molecular dynamics,enables efficient and accurate electronic evolution and sampling.When it is applied to a one-dimension charge-density wave material,carbyne,we are able to compute the spectral function and optical conductivity in the canonical ensemble.The spectral functions evaluated during soliton-antisoliton pair annihilation process reveal significant renormalization of low-energy edge modes due to retarded electron-lattice coupling beyond the Born-Oppenheimer limit.The availability of an efficient and reusable surrogate model for the electronic structure dynamical system will enable calculating many interesting physical properties,paving the way to previously inaccessible or challenging avenues in materials modeling.第一性原理分子动力学模拟过程中产生海量包含丰富电子结构信息的数据,未被充分利用.本文提出一种通过预测晶体材料紧束缚模型的形式,高效、准确地表达第一性原理电子结构的神经网络方法TBworks.TBworks可以结合机器学习分子动力学方法,快速实现复杂体系的分子动力学模拟和电子结构采样,计算电子关联函数以及相应的物理性质.以一维电荷密度波材料碳炔链为应用示例,本文基于TBworks研究了正则系综下的电子谱函数和光电导率,以及孤子-反孤子对湮灭的动力学过程中电子的非绝热演化,发现由于超越波恩-奥本海默近似的动力学效应对电子谱函数的低能模式的修正.该方法为研究动力学体系提供了准确、高效、可重复使用的第一性原理电子结构的代理模型,极大地提高了电子结构的计算效率和模拟尺度,使得对一些由于计算瓶颈无法或者难以进行的新奇性质和现象的研究成为可能.

关 键 词：Neural network Tight-binding model Electronic structure ab initio molecular dynamics 

分 类 号：O469[理学—凝聚态物理] TP183[理学—电子物理学]