Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations

2020/03/04 by Xiaowei Xie, Kristin A. Persson, Xie, Xiaowei +3 · 1 citation
Materials Science · Physics and Astronomy · #Machine Learning in Materials Science #Advanced Chemical Physics Studies #X-ray Diffraction in Crystallography

paper · pdf · doi:10.48550/arxiv.2003.01893

Abstract

Machine Learning (ML) approximations to Density Functional Theory (DFT) potential energy surfaces (PESs) are showing great promise for reducing the computational cost of accurate molecular simulations, but at present they are not applicable to varying electronic states, and in particular, they are not well suited for molecular systems in which the local electronic structure is sensitive to the medium to long-range electronic environment. With this issue as the focal point, we present a new Machine Learning approach called bpopNN for obtaining efficient approximations to DFT PESs. The methodology is based on approaching the true DFT energy as a function of electron populations on atoms, which may be realized in practice with constrained DFT (CDFT). The new approach creates approximations to this function with deep neural networks. These approximations thereby incorporate electronic information naturally into a ML approach, and optimizing the model energy with respect to populations allows the electronic terms to self-consistently adapt to the environment, as in DFT. We confirm the effectiveness of this approach with a variety of calculations on Li_nH_n clusters.

Citations

• Effect of the damping function in dispersion corrected density functional theory
• Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force Fields
• SchNet – A deep learning architecture for molecules and materials
• Less is more: Sampling chemical space with active learning

Cited by

• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials

Related

• Physical machine learning outperforms "human learning" in Quantum Chemistry
• Constructing high‐dimensional neural network potentials: A tutorial review
• Stable and Accurate Orbital-Free DFT Powered by Machine Learning
• Machine Learning Electronic Structure Methods Based On The One-Electron Reduced Density Matrix
• Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces