Uncertainty quantification in molecular simulations with dropout neural network potentials
Uncertainty quantification in molecular simulations with dropout neural network potentials
复制标题
DOI：
10.1038/s41524-020-00390-8
复制
发表时间：
2020-03
影响因子：
9.7
通讯作者：
Mingjian Wen;E. Tadmor
中科院分区：
文献类型：
--
作者：
Mingjian Wen;E. Tadmor
机器学习原子间势(IP)可以提供接近第一性原理方法的精度，例如密度泛函理论(DFT)，而计算成本只有它的一小部分。这极大地扩展了精确分子模拟的范围，为在迄今为止DFT方法无法达到的规模上进行材料和器件的定量设计提供了机会。然而，机器学习IP有一个基本的限制，因为他们缺乏被预测的现象的物理模型，因此在他们的训练集之外进行外推时具有未知的准确性。在这篇文章中，我们提出了一类Dropout不确定性神经网络(Dunn)势，它提供了严格的不确定性估计，可以从贝叶斯和频率统计的角度来理解。作为一个例子，我们开发了碳的邓恩势，并展示了如何用它来预测静态和动态性质的不确定性，包括应力和石墨烯中的声子弥散。我们演示了两种将势能和原子力中的不确定性传播到预测性质的方法。此外，我们还证明了Dunn不确定性估计可以用于检测训练集之外的配置，并且在某些情况下，可以作为计算精度的预测器。
Machine learning interatomic potentials (IPs) can provide accuracy close to that of first-principles methods, such as density functional theory (DFT), at a fraction of the computational cost. This greatly extends the scope of accurate molecular simulations, providing opportunities for quantitative design of materials and devices on scales hitherto unreachable by DFT methods. However, machine learning IPs have a basic limitation in that they lack a physical model for the phenomena being predicted and therefore have unknown accuracy when extrapolating outside their training set. In this paper, we propose a class of Dropout Uncertainty Neural Network (DUNN) potentials that provide rigorous uncertainty estimates that can be understood from both Bayesian and frequentist statistics perspectives. As an example, we develop a DUNN potential for carbon and show how it can be used to predict uncertainty for static and dynamical properties, including stress and phonon dispersion in graphene. We demonstrate two approaches to propagate uncertainty in the potential energy and atomic forces to predicted properties. In addition, we show that DUNN uncertainty estimates can be used to detect configurations outside the training set, and in some cases, can serve as a predictor for the accuracy of a calculation.