Departments of Chemistry and of Physics, University of California, Irvine, California 92697, USA.
Institute of Pharmaceutical Sciences, ETH Zurich, 8093 Zürich, Switzerland.
J Chem Phys. 2013 Dec 14;139(22):224104. doi: 10.1063/1.4834075.
Using a one-dimensional model, we explore the ability of machine learning to approximate the non-interacting kinetic energy density functional of diatomics. This nonlinear interpolation between Kohn-Sham reference calculations can (i) accurately dissociate a diatomic, (ii) be systematically improved with increased reference data and (iii) generate accurate self-consistent densities via a projection method that avoids directions with no data. With relatively few densities, the error due to the interpolation is smaller than typical errors in standard exchange-correlation functionals.
我们使用一维模型来探索机器学习在逼近双原子分子的无相互作用动能密度泛函方面的能力。这种 Kohn-Sham 参考计算之间的非线性插值可以 (i) 准确地离解双原子，(ii) 通过避免无数据方向的投影方法，随着参考数据的增加而系统地改进，以及 (iii) 生成准确的自洽密度。使用相对较少的密度，插值引起的误差小于标准交换相关泛函中的典型误差。
