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

TL;DR

This paper presents a neural network model that accurately represents electronic structures from ab initio molecular dynamics, enabling efficient simulations of electronic properties in crystalline materials.

Contribution

The authors develop a transferable neural network-based representation of ab initio electronic structure data as tight-binding Hamiltonians for crystalline materials, enhancing simulation efficiency.

Findings

Successfully computed spectral functions and optical conductivity for carbyne.

Revealed renormalization of low-energy edge modes during soliton-antisoliton annihilation.

Demonstrated the model's potential for calculating complex physical properties.

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.