arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.03860physics.comp-phphysics.chem-ph
收藏

交换相关泛函的神经网络插值

Neural network interpolation of exchange-correlation functional

Alexander Ryabov, Iskander Akhatov, Petr Zhilyaev

摘要:

密度泛函理论(DFT)是求解多体薛定谔方程最常用的方法之一。DFT理论中的核心不确定性是交换相关(XC)泛函,其确切形式仍然未知。因此,DFT成功的关键部分是基于XC近似的发展。传统上,它们是建立在低密度和高密度极限的解析解上的,并且是量子蒙特卡罗数值计算的结果。然而,XC插值和函数表示还没有一致的通用方案。许多不同的参数化方法主要利用一些唯象规则来构造特定的XC泛函。相比之下,神经网络(NN)方法可以提供一种通用的方法来参数化XC功能,而无需任何先验知识的功能形式。在这项工作中,我们开发NN XC泛函,并证明其适用于三维物理系统。我们表明,局域密度近似(LDA)和广义梯度近似(GGA)的神经网络方法很好地再现。结果表明,局部环境可以很容易地被认为是通过改变的神经网络的第一层中的神经元的数量。开发的NN XC泛函在应用于训练/测试数据中未呈现的系统时显示出良好的结果。制定NN XC框架的普遍性使我们相信,它可以提供优越的结果相比,传统的XC计划提供的训练数据,从高层次的理论,如量子蒙特卡罗和后Hartree-Fock方法。

英文摘要:

Density functional theory (DFT) is one of the most widely used tools to solve the many-body Schrodinger equation. The core uncertainty inside DFT theory is the exchange-correlation (XC) functional, the exact form of which is still unknown. Therefore, the essential part of DFT success is based on the progress in the development of XC approximations. Traditionally, they are built upon analytic solutions in low- and high-density limits and result from quantum Monte Carlo numerical calculations. However, there is no consistent and general scheme of XC interpolation and functional representation. Many different developed parametrizations mainly utilize a number of phenomenological rules to construct a specific XC functional. In contrast, the neural network (NN) approach can provide a general way to parametrize an XC functional without any a priori knowledge of its functional form. In this work, we develop NN XC functionals and prove their applicability to 3-dimensional physical systems. We show that both the local density approximation (LDA) and generalized gradient approximation (GGA) are well reproduced by the NN approach. It is demonstrated that the local environment can be easily considered by changing only the number of neurons in the first layer of the NN. The developed NN XC functionals show good results when applied to systems that are not presented in the training/test data. The generalizability of the formulated NN XC framework leads us to believe that it could give superior results in comparison with traditional XC schemes provided training data from high-level theories such as the quantum Monte Carlo and post-Hartree-Fock methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑