Quantum chemical accuracy from density functional approximations via machine learning.
Quantum chemical accuracy from density functional approximations via machine learning.
复制标题
DOI：
10.1038/s41467-020-19093-1
复制
发表时间：
2020-10-16
影响因子：
16.6
通讯作者：
Burke K
中科院分区：
文献类型：
--
作者：
Bogojeski M;Vogt-Maranto L;Tuckerman ME;Müller KR;Burke K
科恩-沙姆密度泛函理论（英语：Kohn-Sham density functional theory，简称DFT）是大多数化学分支的标准工具，但目前可用的泛函对许多分子的精确度仅限于2-3 kcal·mol−1。从头算方法，如耦合簇，通常产生更高的精度，但计算成本限制了它们的应用小分子。在本文中，我们利用机器学习从DFT密度计算耦合团簇能量，在测试数据上达到量子化学精度（误差低于1 kcal·mol−1）。此外，基于密度的Δ-学习（仅学习标准DFT计算的校正，称为Δ-DFT）显着减少了所需的训练数据量，特别是当包括分子对称性时。通过校正间苯二酚（C6 H4（OH）2）的基于DFT的分子动力学（MD）模拟以获得具有耦合簇精确度的MD轨迹，突出了Δ-DFT的鲁棒性。因此，我们得出结论，Δ-DFT有助于运行具有量子化学精度的气相MD模拟，即使对于标准DFT失败的应变几何形状和构象变化。高级从头计算量子化学方法具有很高的计算负担，从而限制了它们的适用性。在这里，作者使用机器学习来生成化学精确度的耦合簇能量和力，用于DFT密度的几何优化和分子动力学。
Kohn-Sham density functional theory (DFT) is a standard tool in most branches of chemistry, but accuracies for many molecules are limited to 2-3 kcal ⋅ mol−1 with presently-available functionals. Ab initio methods, such as coupled-cluster, routinely produce much higher accuracy, but computational costs limit their application to small molecules. In this paper, we leverage machine learning to calculate coupled-cluster energies from DFT densities, reaching quantum chemical accuracy (errors below 1 kcal ⋅ mol−1) on test data. Moreover, density-based Δ-learning (learning only the correction to a standard DFT calculation, termed Δ-DFT ) significantly reduces the amount of training data required, particularly when molecular symmetries are included. The robustness of Δ-DFT is highlighted by correcting “on the fly” DFT-based molecular dynamics (MD) simulations of resorcinol (C6H4(OH)2) to obtain MD trajectories with coupled-cluster accuracy. We conclude, therefore, that Δ-DFT facilitates running gas-phase MD simulations with quantum chemical accuracy, even for strained geometries and conformer changes where standard DFT fails. High-level ab initio quantum chemical methods carry a high computational burden, thus limiting their applicability. Here, the authors employ machine learning to generate coupled-cluster energies and forces at chemical accuracy for geometry optimization and molecular dynamics from DFT densities.
登录
查看更多内容
影响因子：
2.1
作者：
Bahn, SR;Jacobsen, KW
通讯作者：
Jacobsen, KW
影响因子：
6.3
作者：
Chmiela, Stefan;Sauceda, Huziel E.;Tkatchenko, Alexandre
通讯作者：
Tkatchenko, Alexandre
影响因子：
8.4
作者：
Gastegger M;Behler J;Marquetand P
通讯作者：
Marquetand P
影响因子：
3.7
作者：
Goedecker, S;Teter, M;Hutter, J
通讯作者：
Hutter, J
影响因子：
3.3
作者：
De, Sandip;Bartok, Albert P.;Ceriotti, Michele
通讯作者：
Ceriotti, Michele