Self-learning hybrid Monte Carlo: A first-principles approach
Self-learning hybrid Monte Carlo: A first-principles approach
复制标题
DOI：
10.1103/physrevb.102.041124
复制
发表时间：
2019-09
影响因子：
3.7
通讯作者：
Y. Nagai;M. Okumura;Keita Kobayashi;M. Shiga
中科院分区：
文献类型：
--
作者：
Y. Nagai;M. Okumura;Keita Kobayashi;M. Shiga
我们提出了一种新的方法，称为自学习混合蒙特卡罗（SLHMC），这是一种通用的方法，利用机器学习的潜力，以加快第一性原理密度泛函理论（DFT）模拟的统计采样。轨迹在近似机器学习（ML）势能表面上生成。基于DFT能量的大都会算法接受或拒绝轨迹。这样，对于给定的热力学条件，在DFT水平上对统计系综进行精确采样。同时，通过训练来提高ML潜力，以增强采样，从而自动创建从精确集合中采样的训练数据集。使用的例子$\alpha$-石英晶体SiO$_2^{}$和声子介导的非常规超导体YNi$_2^{}$B$_2^{}$C系统，我们表明，SLHMC与人工神经网络（ANN）是能够非常有效的采样，而在同一时间，使优化的ANN潜力meV/原子的精度。由此得到的ANN潜力是可转移的ANN分子动力学模拟探索动力学以及热力学。这使得SLHMC方法广泛适用于物理和化学材料的研究。
We propose a novel approach called Self-Learning Hybrid Monte Carlo (SLHMC) which is a general method to make use of machine learning potentials to accelerate the statistical sampling of first-principles density-functional-theory (DFT) simulations. The trajectories are generated on an approximate machine learning (ML) potential energy surface. The trajectories are then accepted or rejected by the Metropolis algorithm based on DFT energies. In this way the statistical ensemble is sampled exactly at the DFT level for a given thermodynamic condition. Meanwhile the ML potential is improved on the fly by training to enhance the sampling, whereby the training data set, which is sampled from the exact ensemble, is created automatically. Using the examples of $\alpha$-quartz crystal SiO$_2^{}$ and phonon-mediated unconventional superconductor YNi$_2^{}$B$_2^{}$C systems, we show that SLHMC with artificial neural networks (ANN) is capable of very efficient sampling, while at the same time enabling the optimization of the ANN potential to within meV/atom accuracy. The ANN potential thus obtained is transferable to ANN molecular dynamics simulations to explore dynamics as well as thermodynamics. This makes the SLHMC approach widely applicable for studies on materials in physics and chemistry.