Convolutional network learning of self-consistent electron density via grid-projected atomic fingerprints

Abstract

The self-consistent field (SCF) generation of the three-dimensional (3D) electron density distribution ($\rho$) represents a fundamental aspect of density functional theory (DFT) and related first-principles calculations, and how one can shorten or bypass the SCF loop represents a critical question from both practical and fundamental standpoints. Herein, a machine learning strategy DeepSCF is presented in which the map between the SCF $\rho$ and the initial guess density (${\rho }_0$) constructed by the summation of neutral atomic densities is learned using 3D convolutional neural networks (CNNs). High accuracy and transferability of DeepSCF are achieved by expanding the input features to include atomic fingerprints beyond ${\rho }_0$ and encoding them on a 3D grid. The prediction of the residual density ($\delta \rho$) rather than $\rho$ itself is targeted, and, since $\delta \rho$ corresponds to chemical bonding information, a dataset of small-sized organic molecules featuring diverse bonding characters is adopted. After enhancing the fidelity of the method by subjecting the atomic geometries in the dataset to random strains and rotations, the effectiveness of DeepSCF is finally demonstrated using a complex large carbon nanotube-based DNA sequencer model. This work evidences that the nearsightedness in electronic structures can be optimally represented via the local connectivity in CNNs.

arXiv comment9 pages, 6 figures

References in corpus (20)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• The SIESTA method for ab initio order-N materials simulation
• Efficient index handling of multidimensional periodic boundary conditions
• By-passing the Kohn-Sham equations with machine learning
• Nearsightedness of Electronic Matter
• More is the Same; Phase Transitions and Mean Field Theories
• Machine learning and density functional theory
• Predicting electronic structures at any length scale with machine learning
• Predicting charge density distribution of materials using a local-environment-based graph convolutional network
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• Recent progress in atomistic simulation of electrical current DNA sequencing
• Extensive deep neural networks for transferring small scale learning to large scale systems
• Computing the Self-Consistent Field in Kohn-Sham Density Functional Theory
• One-way multigrid method in electronic structure calculations
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Distinct mechanisms of DNA sensing based on N-doped carbon nanotubes with enhanced conductance and chemical selectivity
• Predicting The One-Particle Density Matrix With Machine Learning
• Nitrogen doping of carbon nanoelectrodes for enhanced control of DNA translocation dynamics
• Object-oriented construction of a multigrid electronic-structure code with Fortran 90
• Impact of quantum-chemical metrics on the machine learning prediction of electron density

Cited by in corpus (1)

• A charge-density machine-learning workflow for computing the infrared spectrum of molecules