海归学者发起的公益学术平台
分享信息,整合资源

交流学术,偶尔风月
紧束缚方法是目前确定大型系统的电子和传输特性的主流方法。在紧束缚方法中,系统被描述为一组参数化的实空间哈密顿量矩阵。其参数的选择决定了计算的可靠性。传统的经验紧束缚方法直接利用现有的参数集构造紧束缚哈密顿量,在未经特定优化的情况下,很难定量地再现所需的能带结构。而近年来兴起的从头计算紧束缚方法则可以通过基函数变换,从第一性原理计算结果中得到紧束缚参数,具有较高的数值精度。然而,该方法依赖于对基组的先验知识,同时也相对耗时。如何在无需先验知识的情况下,快速方便地得到能够还原给定能带结构的紧束缚参数就成为一个重要的研究课题。
来自武汉大学物理科学与技术学院的常胜教授团队,通过引入机器学习工具,提出了一种构造紧束缚哈密顿量的神经网络, 该网络模型将神经元作为紧束缚哈密顿量的矩阵元素,将给定的从头算能带结构作为训练集,可以直接学习得到紧束缚哈密顿量的在位能与跳跃能。这种动态的、一对一的神经网络能根据预定义的精度,要求自动调整网络中的神经元数量,不需要有对系统基组的先验知识,也不用输入系统的实空间信息,只需要输入想要还原的能带数据作为训练集即可。在InSe纳米带材料上通过与最局域瓦尼尔函数法得到的结果作对比,验证了该机器学习方法构造的紧束缚哈密顿量在计算系统电子和输运特性上的精度和效率。此外,该研究还给出了两种基于所提出的基本网络模型的变体模型,能分别用以优化给定的紧束缚模型,以及生成Slater-Koster形式的紧束缚模型。该研究不仅提出了一种新的构造紧束缚模型的方法,还为机器学习工具运用在物理问题中提供了新的见解。
该文近期发表于npj Computational Materials 7: 11 (2021),英文标题与摘要如下,点击左下角“阅读原文”可以自由获取论文PDF。
Machine learning method for tight-binding Hamiltonian parameterization from ab-initio band structure 
Zifeng Wang, Shizhuo Ye, Hao Wang, Jin He, Qijun Huang & Sheng Chang 
The tight-binding (TB) method is an ideal candidate for determining electronic and transport properties for a large-scale system. It describes the system as real-space Hamiltonian matrices expressed on a manageable number of parameters, leading to substantially lower computational costs than the ab-initio methods. Since the whole system is defined by the parameterization scheme, the choice of the TB parameters decides the reliability of the TB calculations. The typical empirical TB method uses the TB parameters directly from the existing parameter sets, which hardly reproduces the desired electronic structures quantitatively without specific optimizations. It is thus not suitable for quantitative studies like the transport property calculations. The ab-initio TB method derives the TB parameters from the ab-initio results through the transformation of basis functions, which achieves much higher numerical accuracy. However, it assumes prior knowledge of the basis and may encompass truncation error. Here, a machine learning method for TB Hamiltonian parameterization is proposed, within which a neural network (NN) is introduced with its neurons acting as the TB matrix elements. This method can construct the empirical TB model that reproduces the given ab-initio energy bands with predefined accuracy, which provides a fast and convenient way for TB model construction and gives insights into machine learning applications in physical problems. 
本文系网易新闻·网易号“各有态度”特色内容
媒体转载联系授权请看下方
继续阅读
阅读原文