Skip to main content
QUICK REVIEW

[论文解读] Physical machine learning outperforms "human learning" in Quantum Chemistry

Anton V. Sinitskiy, Vijay S. Pande|arXiv (Cornell University)|Aug 1, 2019
Machine Learning in Materials Science参考文献 121被引用 4
一句话总结

本文提出了一种物理信息机器学习框架,结合了高水平量子化学的准确性与神经网络的高效性。通过推广Hohenberg-Kohn定理,作者推导出电子密度和能量的精确方程,使深度神经网络能够以低至0.9 kcal/mol的平均绝对误差预测分子性质——其精度超越了DFT和现有机器学习方法,同时保持了较低的计算成本。

ABSTRACT

Two types of approaches to modeling molecular systems have demonstrated high practical efficiency. Density functional theory (DFT), the most widely used quantum chemical method, is a physical approach predicting energies and electron densities of molecules. Recently, numerous papers on machine learning (ML) of molecular properties have also been published. ML models greatly outperform DFT in terms of computational costs, and may even reach comparable accuracy, but they are missing physicality - a direct link to Quantum Physics - which limits their applicability. Here, we propose an approach that combines the strong sides of DFT and ML, namely, physicality and low computational cost. By generalizing the famous Hohenberg-Kohn theorems, we derive general equations for exact electron densities and energies that can naturally guide applications of ML in Quantum Chemistry. Based on these equations, we build a deep neural network that can compute electron densities and energies of a wide range of organic molecules not only much faster, but also closer to exact physical values than current versions of DFT. In particular, we reached a mean absolute error in energies of molecules with up to eight non-hydrogen atoms as low as 0.9 kcal/mol relative to CCSD(T) values, noticeably lower than those of DFT (down to ~3 kcal/mol on the same set of molecules) and ML (down to ~1.5 kcal/mol) methods. A simultaneous improvement in the accuracy of predictions of electron densities and energies suggests that the proposed approach describes the physics of molecules better than DFT functionals developed by "human learning" earlier. Thus, physics-based ML offers exciting opportunities for modeling, with high-theory-level quantum chemical accuracy, of much larger molecular systems than currently possible.

研究动机与目标

  • 开发一种机器学习方法,保留量子力学的物理严谨性,同时实现计算效率。
  • 通过将基本量子力学原理嵌入神经网络架构,克服传统DFT和机器学习方法的局限性。
  • 证明物理引导的机器学习在分子能量和电子密度预测方面可超越人工优化的DFT泛函。
  • 实现对以往传统量子化学方法难以处理的大规模分子体系的高精度建模。

提出的方法

  • 作者推广Hohenberg-Kohn定理,推导出电子密度和能量相对于外势的精确解析表达式。
  • 利用这些精确方程训练深度神经网络,直接从分子几何结构和原子核电荷预测电子密度和能量。
  • 通过损失函数强制实施物理一致性,基于推导出的精确方程进行端到端训练。
  • 在包含最多八个非氢原子的多样化有机分子上评估模型,以CCSD(T)作为参考。
  • 网络架构设计为对分子对称性不变,并尊重量子力学的变分原理。
  • 通过将基本物理定律嵌入网络的归纳偏置中,避免依赖经验数据拟合。

实验结果

研究问题

  • RQ1基于精确量子力学原理训练的机器学习模型是否能在分子能量预测方面超越人工优化的DFT泛函?
  • RQ2与标准机器学习和DFT相比,物理信息神经网络在电子密度和能量预测精度方面能提升多少?
  • RQ3深度学习模型能否在保持计算效率的同时,实现接近CCSD(T)的精度,适用于更大分子?
  • RQ4将Hohenberg-Kohn定理嵌入神经网络架构是否能带来更好的泛化能力和物理一致性?

主要发现

  • 所提出的物理信息机器学习模型在分子能量预测中实现了0.9 kcal/mol的平均绝对误差,显著低于DFT(约3 kcal/mol)和现有机器学习方法(约1.5 kcal/mol)。
  • 该模型在电子密度和能量预测方面同时提升了精度,表明其物理描述比人工学习的DFT泛函更加一致。
  • 该方法达到了接近CCSD(T)参考精度——被视为黄金标准——同时比传统高水平量子化学方法快几个数量级。
  • 神经网络在多样化有机分子上表现出良好的泛化能力,展现出超越训练数据的鲁棒性和可迁移性。
  • 结果表明,通过将精确物理定律嵌入模型架构,物理引导的机器学习可超越‘人类学习’在量子化学中的表现。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。