Deep Density: circumventing the Kohn-Sham equations via symmetry preserving neural networks

The recently developed Deep Potential [Phys. Rev. Lett. 120, 143001, 2018] is a powerful method to represent general inter-atomic potentials using deep neural networks. The success of Deep Potential rests on the proper treatment of locality and symmetry properties of each component of the network. In this paper, we leverage its network structure to effectively represent the mapping from the atomic configuration to the electron density in Kohn-Sham density function theory (KS-DFT). By directly targeting at the self-consistent electron density, we demonstrate that the adapted network architecture, called the Deep Density, can effectively represent the electron density as the linear combination of contributions from many local clusters. The network is constructed to satisfy the translation, rotation, and permutation symmetries, and is designed to be transferable to different system sizes. We demonstrate that using a relatively small number of training snapshots, Deep Density achieves excellent performance for one-dimensional insulating and metallic systems, as well as systems with mixed insulating and metallic characters. We also demonstrate its performance for real three-dimensional systems, including small organic molecules, as well as extended systems such as water (up to $512$ molecules) and aluminum (up to $256$ atoms).

[1]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[2]  S. Goedecker.  Linear scaling electronic structure methods , 1999 .

[3]  N. Mermin.  Thermal Properties of the Inhomogeneous Electron Gas , 1965 .

[4]  Berend Smit,et al.  Understanding molecular simulation: from algorithms to applications , 1996 .

[5]  Klaus-Robert Müller,et al.  SchNet: A continuous-filter convolutional neural network for modeling quantum interactions , 2017, NIPS.

[6]  E Weinan,et al.  End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems , 2018, NeurIPS.

[7]  David A. Strubbe,et al.  Deep learning and density-functional theory , 2018, Physical Review A.

[8]  D. Bowler,et al.  O(N) methods in electronic structure calculations. , 2011, Reports on progress in physics. Physical Society.

[9]  Alberto Fabrizio,et al.  Electron density learning of non-covalent systems , 2019, Chemical science.

[10]  E. Weinan,et al.  Deep Potential: a general representation of a many-body potential energy surface , 2017, 1707.01478.

[11]  E Weinan,et al.  DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics , 2017, Comput. Phys. Commun..

[12]  Alberto Fabrizio,et al.  Transferable Machine-Learning Model of the Electron Density , 2018, ACS central science.

[13]  Lexing Ying,et al.  Numerical methods for Kohn–Sham density functional theory , 2019, Acta Numerica.

[14]  D. Hamann.  Optimized norm-conserving Vanderbilt pseudopotentials , 2013, 1306.4707.

[15]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[16]  Li Li,et al.  Efficient prediction of 3D electron densities using machine learning , 2018, 1811.06255.

[17]  W. Kohn,et al.  Nearsightedness of electronic matter. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[18]  P. Hohenberg,et al.  Inhomogeneous Electron Gas , 1964 .

[19]  R. Bartlett,et al.  Coupled-cluster theory in quantum chemistry , 2007 .

[20]  Kohn,et al.  Density functional and density matrix method scaling linearly with the number of atoms. , 1996, Physical review letters.

[21]  Donald G. M. Anderson.  Iterative Procedures for Nonlinear Integral Equations , 1965, JACM.

[22]  Francois Gygi,et al.  Optimization algorithm for the generation of ONCV pseudopotentials , 2015, Comput. Phys. Commun..

[23]  Chao Yang,et al.  DGDFT: A massively parallel method for large scale density functional theory calculations. , 2015, The Journal of chemical physics.

[24]  J S Smith,et al.  ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost , 2016, Chemical science.

[25]  Xavier Gonze,et al.  Dynamical matrices, born effective charges, dielectric permittivity tensors, and interatomic force constants from density-functional perturbation theory , 1997 .

[26]  Burke,et al.  Generalized Gradient Approximation Made Simple. , 1996, Physical review letters.

[27]  Chao Yang,et al.  Elliptic Preconditioner for Accelerating the Self-Consistent Field Iteration in Kohn-Sham Density Functional Theory , 2012, SIAM J. Sci. Comput..

[28]  Blöchl,et al.  Projector augmented-wave method. , 1994, Physical review. B, Condensed matter.

[29]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[30]  Li Li,et al.  Bypassing the Kohn-Sham equations with machine learning , 2016, Nature Communications.

[31]  M. Rupp,et al.  Machine learning of molecular electronic properties in chemical compound space , 2013, 1305.7074.

[32]  E Weinan,et al.  Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation , 2018, Physical Review Materials.

[33]  E Weinan,et al.  Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics , 2017, Physical review letters.

[34]  Klaus-Robert Müller,et al.  Machine learning of accurate energy-conserving molecular force fields , 2016, Science Advances.

[35]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[36]  White,et al.  Density matrix formulation for quantum renormalization groups. , 1992, Physical review letters.

[37]  R. Martin,et al.  Electronic Structure: Basic Theory and Practical Methods , 2004 .

[38]  Kresse,et al.  Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. , 1996, Physical review. B, Condensed matter.

[39]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Eguiluz.  Self-consistent static-density-response function of a metal surface in density-functional theory. , 1985, Physical review. B, Condensed matter.

[41]  W. Kohn,et al.  Self-Consistent Equations Including Exchange and Correlation Effects , 1965 .

[42]  Alexander J. Smola,et al.  Deep Sets , 2017, 1703.06114.