Uncertainty-aware molecular dynamics from Bayesian active learning for phase transformations and thermal transport in SiC
Uncertainty-aware molecular dynamics from Bayesian active learning for phase transformations and thermal transport in SiC
复制标题
DOI：
10.1038/s41524-023-00988-8
复制
发表时间：
2022-03
影响因子：
9.7
通讯作者：
Yu Xie;Jonathan Vandermause;Senja Ramakers;N. Protik;A. Johansson;B. Kozinsky
中科院分区：
文献类型：
--
作者：
Yu Xie;Jonathan Vandermause;Senja Ramakers;N. Protik;A. Johansson;B. Kozinsky
机器学习原子间力场有望在量子相互作用建模和模拟原子动力学方面结合高计算效率和准确性。主动学习方法最近已经被开发来有效地和自动地训练力场。其中，贝叶斯主动学习利用原则性不确定性量化来进行数据采集决策。在这项工作中，我们提出了一个一般的贝叶斯主动学习工作流程，力场是从一个稀疏高斯过程回归模型的基础上原子簇扩展描述符。为了规避稀疏高斯过程不确定性计算的高计算成本，我们制定了一个高性能的近似映射的不确定性，并证明了几个数量级的加速。我们展示了自主的主动学习工作流程，通过训练碳化硅（SiC）多晶型物的贝叶斯力场模型，在短短几天的计算机时间，并显示压力引起的相变被准确捕获。由此产生的模型表现出密切的协议与从头计算和实验测量，并优于现有的经验模型的振动和热性能。主动学习工作流程很容易推广到广泛的材料系统，并加速其计算理解。
Machine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomistic dynamics. Active learning methods have been recently developed to train force fields efficiently and automatically. Among them, Bayesian active learning utilizes principled uncertainty quantification to make data acquisition decisions. In this work, we present a general Bayesian active learning workflow, where the force field is constructed from a sparse Gaussian process regression model based on atomic cluster expansion descriptors. To circumvent the high computational cost of the sparse Gaussian process uncertainty calculation, we formulate a high-performance approximate mapping of the uncertainty and demonstrate a speedup of several orders of magnitude. We demonstrate the autonomous active learning workflow by training a Bayesian force field model for silicon carbide (SiC) polymorphs in only a few days of computer time and show that pressure-induced phase transformations are accurately captured. The resulting model exhibits close agreement with both ab initio calculations and experimental measurements, and outperforms existing empirical models on vibrational and thermal properties. The active learning workflow readily generalizes to a wide range of material systems and accelerates their computational understanding.