Bridging deep learning force fields and electronic structures with a physics-informed approach

TL;DR

This paper introduces a physics-informed neural network that integrates deep-learning force fields with electronic structure simulations, enabling efficient analysis of large-scale, low-periodicity material systems.

Contribution

It presents a novel multimodal machine-learning framework combining force field and electronic structure modeling using Wannier functions, enhancing efficiency and predictive capabilities.

Findings

Improved efficiency in simulating large-scale systems.

Enhanced ability to predict electronic properties.

Integration of electronic structure capabilities into force field models.

Abstract

This work presents a physics-informed neural network approach bridging deep-learning force field and electronic structure simulations, illustrated through twisted two-dimensional large-scale material systems. The deep potential molecular dynamics model is adopted as the backbone, and electronic structure simulation is integrated. Using Wannier functions as the basis, we categorize Wannier Hamiltonian elements based on physical principles to incorporate diverse information from a deep-learning force field model. This information-sharing mechanism streamlines the architecture of our multifunctional model, enhancing its efficiency and effectiveness. Utilizing Wannier functions as the basis lays the groundwork for predicting more physical quantities. This approach serves as a powerful tool to explore both the structural and electronic properties of large-scale systems characterized by low periodicities. By endowing an existing well-developed machine-learning force field with electronic structure simulation capabilities, the study marks a significant advancement in developing multimodal machine-learning-based computational methods that can achieve multiple functionalities traditionally exclusive to first-principles calculations.