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.)
Efficient Construction of Excited-State Hessian Matrices with Machine Learning Accelerated Multilayer Energy-Based Fragment Method.
The Journal of Physical Chemistry A ( IF 2.7 ) Pub Date : 2020-06-12 , DOI: 10.1021/acs.jpca.0c04117 Wen-Kai Chen 1 , Yaolong Zhang 2 , Bin Jiang 2 , Wei-Hai Fang 1 , Ganglong Cui 1
The Journal of Physical Chemistry A ( IF 2.7 ) Pub Date : 2020-06-12 , DOI: 10.1021/acs.jpca.0c04117 Wen-Kai Chen 1 , Yaolong Zhang 2 , Bin Jiang 2 , Wei-Hai Fang 1 , Ganglong Cui 1
Affiliation
|
Recently, we have developed a multilayer energy-based fragment (MLEBF) method to describe excited states of large systems in which photochemically active and inert regions are separately treated with multiconfigurational and single-reference electronic structure method and their mutual polarization effects are naturally described within the many-body expansion framework. This MLEBF method has been demonstrated to provide highly accurate energies and gradients. In this work, we have further derived the MLEBF method with which highly accurate excited-state Hessian matrices of large systems are efficiently constructed. Moreover, in combination with recently proposed embedded atom neural network (EANN) model we have developed a machine learning (ML) accelerated MLEBF method (i.e., ML-MLEBF) in which photochemically inert region is entirely replaced with trained ML models. ML-MLEBF is found to improve computational efficiency of Hessian matrices in particular for large systems. Furthermore, both MLEBF and ML-MLEBF methods are highly parallel and exhibit low-scaling computational cost with multiple CPUs. The present developments could motivate combining various ML techniques with fragment-based electronic structure methods to explore Hessian-matrix-based excited-state properties of large systems.
中文翻译：
机器学习加速多层基于能量的碎片方法可有效构造激发态的黑森州矩阵。
最近，我们开发了一种基于多层能量的碎片（MLEBF）方法来描述大型系统的激发态，在该系统中，用多构型和单参比电子结构方法分别处理了光化学活性和惰性区域，并且它们的相互极化效应自然被描述为多主体扩展框架。该MLEBF方法已被证明可提供高度准确的能量和梯度。在这项工作中，我们进一步推导了MLEBF方法，该方法可以有效地构建大型系统的高精度激发态Hessian矩阵。此外，结合最近提出的嵌入式原子神经网络（EANN）模型，我们开发了一种机器学习（ML）加速MLEBF方法（即，ML-MLEBF），其中光化学惰性区域被训练有素的ML模型完全取代。发现ML-MLEBF可以提高Hessian矩阵的计算效率，特别是对于大型系统。此外，MLEBF和ML-MLEBF方法都是高度并行的，并且在多个CPU上的计算成本较低。当前的发展可能会促使各种ML技术与基于片段的电子结构方法相结合，以探索大型系统基于Hessian矩阵的激发态性质。
更新日期：2020-07-09
中文翻译：
机器学习加速多层基于能量的碎片方法可有效构造激发态的黑森州矩阵。
最近，我们开发了一种基于多层能量的碎片（MLEBF）方法来描述大型系统的激发态，在该系统中，用多构型和单参比电子结构方法分别处理了光化学活性和惰性区域，并且它们的相互极化效应自然被描述为多主体扩展框架。该MLEBF方法已被证明可提供高度准确的能量和梯度。在这项工作中，我们进一步推导了MLEBF方法，该方法可以有效地构建大型系统的高精度激发态Hessian矩阵。此外，结合最近提出的嵌入式原子神经网络（EANN）模型，我们开发了一种机器学习（ML）加速MLEBF方法（即，ML-MLEBF），其中光化学惰性区域被训练有素的ML模型完全取代。发现ML-MLEBF可以提高Hessian矩阵的计算效率，特别是对于大型系统。此外，MLEBF和ML-MLEBF方法都是高度并行的，并且在多个CPU上的计算成本较低。当前的发展可能会促使各种ML技术与基于片段的电子结构方法相结合，以探索大型系统基于Hessian矩阵的激发态性质。
京公网安备 11010802027423号