当前位置: X-MOL 学术J. Phys. Chem. A › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improving the Performance of Long-Range-Corrected Exchange-Correlation Functional with an Embedded Neural Network
The Journal of Physical Chemistry A ( IF 2.7 ) Pub Date : 2017-09-19 00:00:00 , DOI: 10.1021/acs.jpca.7b07045
Qin Liu 1 , JingChun Wang 1 , PengLi Du 1 , LiHong Hu 2 , Xiao Zheng 1 , GuanHua Chen 3
Affiliation  

A machine-learning-based exchange-correlation functional is proposed for general-purpose density functional theory calculations. It is built upon the long-range-corrected Becke–Lee–Yang–Parr (LC–BLYP) functional, along with an embedded neural network which determines the value of the range-separation parameter μ for every individual system. The structure and the weights of the neural network are optimized with a reference data set containing 368 highly accurate thermochemical and kinetic energies. The newly developed functional (LC–BLYP–NN) achieves a balanced performance for a variety of energetic properties investigated. It largely improves the accuracy of atomization energies and heats of formation on which the original LC–BLYP with a fixed μ performs rather poorly. Meanwhile, it yields a similar or slightly compromised accuracy for ionization potentials, electron affinities, and reaction barriers, for which the original LC–BLYP works reasonably well. This work clearly highlights the potential usefulness of machine-learning techniques for improving density functional calculations.

中文翻译:

嵌入式神经网络提高远程校正的交换相关功能的性能

提出了一种基于机器学习的交换相关函数,用于通用密度泛函理论的计算。它建立在经过远程校正的Becke-Lee-Yang-Parr(LC-BLYP)函数以​​及嵌入式神经网络的基础上,该神经网络确定每个单独系统的距离分离参数μ的值。使用包含368个高精度热化学能和动能的参考数据集对神经网络的结构和权重进行了优化。新开发的功能(LC–BLYP–NN)在研究的各种高能特性方面均达到了平衡的性能。它极大地提高了雾化能量和形成热量的准确性,原始的具有固定μ值的LC–BLYP表现得很差。同时,它对于电离电势,电子亲和力和反应势垒具有相似或略有折衷的精度,因此,原始的LC-BLYP可以很好地工作。这项工作清楚地突出了机器学习技术对改进密度泛函计算的潜在实用性。
更新日期:2017-09-19
down
wechat
bug