Development of a machine learning potential for graphene
Development of a machine learning potential for graphene
复制标题
DOI：
10.1103/physrevb.97.054303
复制
发表时间：
2018-02-05
影响因子：
3.7
通讯作者：
Michaelides, Angelos
中科院分区：
文献类型：
--
作者：
Rowe, Patrick;Csanyi, Gabor;Michaelides, Angelos
我们提出了使用高斯近似势（GAP）机器学习方法构建的准确的石墨烯原子间势。该 GAP 模型获得了密度泛函理论 (DFT) 势能面的忠实表示，有助于高精度（接近从头计算方法的精度）分子动力学模拟。这是以比直接调用电子结构方法的类似计算低几个数量级的计算成本实现的。我们使用实验数据和从头计算数据作为参考，评估我们的机器学习模型以及许多流行的经验和键序势的准确性。我们发现，虽然经验原子间势和参考数据之间以及经验势本身之间存在显着差异，但这里引入的机器学习模型在所有测试领域都提供了示范性的性能。计算的属性包括：0 K 时的石墨烯声子色散曲线（我们以亚兆电子伏的精度进行预测）、有限温度下的声子光谱、与 NPT 从头算分子动力学模拟相比高达 2500 K 的面内热膨胀，以及石墨烯拉曼带热致色散与实验观察结果的比较。
We present an accurate interatomic potential for graphene, constructed using the Gaussian approximation potential (GAP) machine learning methodology. This GAP model obtains a faithful representation of a density functional theory (DFT) potential energy surface, facilitating highly accurate (approaching the accuracy of ab initio methods) molecular dynamics simulations. This is achieved at a computational cost which is orders of magnitude lower than that of comparable calculations which directly invoke electronic structure methods. We evaluate the accuracy of our machine learning model alongside that of a number of popular empirical and bond-order potentials, using both experimental and ab initio data as references. We find that whilst significant discrepancies exist between the empirical interatomic potentials and the reference data-and amongst the empirical potentials themselves-the machine learning model introduced here provides exemplary performance in all of the tested areas. The calculated properties include: graphene phonon dispersion curves at 0 K (which we predict with sub-meV accuracy), phonon spectra at finite temperature, in-plane thermal expansion up to 2500 K as compared to NPT ab initio molecular dynamics simulations and a comparison of the thermally induced dispersion of graphene Raman bands to experimental observations.