Neural network representation of electronic structure from $ab$ $initio$ molecular dynamics

Abstract

Despite their rich information content, electronic structure data amassed at high volumes in $ab$ $initio$ molecular dynamics simulations are generally under-utilized. We introduce a transferable high-fidelity neural network representation of such data in the form of tight-binding Hamiltonians for crystalline materials. This predictive representation of $ab$ $initio$ electronic structure, combined with machine-learning boosted molecular dynamics, enables efficient and accurate electronic evolution and sampling. When applied to a one-dimension charge-density wave material, carbyne, we are able to compute the spectral function and optical conductivity in the canonical ensemble. The spectral functions evaluated during soliton-antisoliton pair annihilation process reveal significant renormalization of low-energy edge modes due to retarded electron-lattice coupling beyond the Born-Oppenheimer limit. The availability of an efficient and reusable surrogate model for the electronic structure dynamical system will enable calculating many interesting physical properties, paving way to previously inaccessible or challenging avenues in materials modeling.

arXiv comment12 pages,11 figures

References in corpus (10)

• Maximally localized Wannier functions: Theory and applications
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Opening the Black Box of Deep Neural Networks via Information
• Exponential localization of Wannier functions in insulators
• Electrical conductivity measured in atomic carbon chains
• Learning the electronic density of states in condensed matter
• Time evolution of the Kondo resonance in response to a quench

Cited by in corpus (7)

• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Deep learning tight-binding approach for large-scale electronic simulations at finite temperatures with $ab$ $initio$ accuracy
• Universal materials model of deep-learning density functional theory Hamiltonian
• Neural-network Density Functional Theory Based on Variational Energy Minimization
• Quadratic Scaling Bosonic Path Integral Molecular Dynamics
• Crystalline Material Discovery in the Era of Artificial Intelligence
• Temperature-transferable tight-binding model using a hybrid-orbital basis