Reducing the Quantum Many-Electron Problem to Two Electrons with Machine Learning
Reducing the Quantum Many-Electron Problem to Two Electrons with Machine Learning
复制标题
通过机器学习将量子多电子问题简化为两个电子
DOI：
10.1021/jacs.2c07112
复制
发表时间：
2022
影响因子：
15
通讯作者：
Mazziotti, David A.
中科院分区：
文献类型：
--
作者：
Sager-Smith, LeeAnn M.;Mazziotti, David A.
化学计算中一个突出的挑战是多电子问题，其中计算方法随着系统规模的扩大而变得令人望而却步。任何分子的能量都可以表示为两个电子波函数的能量的加权和，这些能量只能通过两个电子的计算来计算。尽管这种扩展的“Aufbau”原理在物理上是优雅的，但对于一般分子体系来说，重量和双基职业分布──的确定仍然是难以捉摸的。在这里，我们介绍了一种新的电子结构范例，其中近似的双原子占据分布是通过卷积神经网络来学习的。我们发现，神经网络学习然后可表示的条件，对它的分布的约束来表示神经网络-电子系统。通过对只有2-7个碳原子的碳氢化合物异构体的训练，我们能够预测辛烷异构体的能量以及8-15个碳的碳氢化合物的能量。目前的工作表明，机器学习可以用来将多电子问题归结为一个有效的双电子问题，从而为准确预测电子结构开辟了新的机会。
An outstanding challenge in chemical computation is the many-electron problem where computational methodologies scale prohibitively with system size. The energy of any molecule can be expressed as a weighted sum of the energies of two-electron wave functions that are computable from only a two-electron calculation. Despite the physical elegance of this extended “aufbau” principle, the determination of the distribution of weights─geminal occupations─for general molecular systems has remained elusive. Here we introduce a new paradigm for electronic structure where approximate geminal-occupation distributions are “learned” via a convolutional neural network. We show that the neural network learns theN-representability conditions, constraints on the distribution for it to represent anN-electron system. By training on hydrocarbon isomers with only 2–7 carbon atoms, we are able to predict the energies for isomers of octane as well as hydrocarbons with 8–15 carbons. The present work demonstrates that machine learning can be used to reduce the many-electron problem to an effective two-electron problem, opening new opportunities for accurately predicting electronic structure.