Machine learning exchange-correlation potential in time-dependent density-functional theory

Machine learning exchange-correlation potential in time-dependent density-functional theory
复制标题

时间相关密度泛函理论中的机器学习交换相关势

DOI:
10.1103/physreva.101.050501
复制
发表时间:
2020
期刊:
影响因子:
2.9
通讯作者:
Haruyama Jun
Haruyama Jun
中科院分区:
物理与天体物理2区
文献类型:
--
作者:
Suzuki Yasumitsu;Nagai Ryo;Haruyama Jun

文献摘要

参考文献

相似文献

我们提出了一种基于机器学习的方法来开发时间依赖密度泛函理论(TDDFT)的交换相关势。利用少量的电子-氢散射模型数据,训练神经网络从随时间变化的电子密度映射到随时间变化的Kohn-Sham方程中相应的关联势.我们证明,这种神经网络势可以捕获复杂的结构,在散射过程中的时间相关势,并提供正确的散射动力学,这是不是由标准的绝热泛函。我们还表明,它是可能的,将非绝热(或记忆)的潜在影响与这种机器学习技术,这显着提高了动态的准确性。该方法为改进TDDFT的交换关联势提供了一种途径,使TDDFT理论成为研究各种激发态现象的有力工具。
We propose a machine-learning-based approach to develop the exchange-correlation potential of time-dependent density-functional theory (TDDFT). The neural network projection from the time-varying electron densities to the corresponding correlation potentials in the time-dependent Kohn-Sham equation is trained using a few exact datasets for a model system of electron-hydrogen scattering. We demonstrate that this neural network potential can capture the complex structures in the time-dependent correlation potential during the scattering process and provide correct scattering dynamics, which are not obtained by the standard adiabatic functionals. We also show that it is possible to incorporate the nonadiabatic (ormemory) effect in the potential with this machine learning technique, which significantly improves the accuracy of the dynamics. The method developed here offers a way to improve the exchange-correlation potential of TDDFT, which makes the theory a more powerful tool to study various excited state phenomena.
DOI: 10.1039/c2cp24118h
发表时间: 2012
期刊: Physical chemistry chemical physics : PCCP
影响因子: --
作者:
Lucas Wagner;E. Stoudenmire;K. Burke;S. White
通讯作者: S. White
DOI: 10.1103/physrevb.74.245427
发表时间: 2006-12-01
期刊: PHYSICAL REVIEW B
影响因子: 3.7
作者:
Casula, Michele;Sorella, Sandro;Senatore, Gaetano
通讯作者: Senatore, Gaetano
DOI: 10.1103/physreva.85.052510
发表时间: 2012
期刊: arXiv: Chemical Physics
影响因子: --
作者:
P. Elliott;N. Maitra
通讯作者: N. Maitra
DOI: 10.1103/physrevlett.115.093001
发表时间: 2014
影响因子: 8.6
作者:
C. Pellegrini;Johannes Flick;I. Tokatly;H. Appel;Á. Rubio
通讯作者: Á. Rubio
DOI: --
发表时间: 2018
期刊: European Physical Journal B : Condensed Matter Physics
影响因子: --
作者:
Alina Umerbekova;Shoufeng Zhang;Sudheer Kumar P.;M. Pavanello
通讯作者: M. Pavanello