Graph Neural Network for Unified Electronic and Interatomic Potentials: Strain-tunable Electronic Structures in 2D Materials

2025/10/18 by Moon‐ki Choi, Choi, Moon-ki, Palmer, Daniel +2
Materials Science · Physics and Astronomy · #2D Materials and Applications #Computational Physics (physics.comp-ph) #FOS: Physical sciences #Graphene research and applications #Materials Science (cond-mat.mtrl-sci) #Topological Materials and Phenomena

paper · pdf · doi:10.48550/arxiv.2510.16605

openalex publication_date 2025/10/18 · openalex created_date 2025/10/22 · openalex updated_date 2026/07/28

Abstract

We introduce UEIPNet, an equivariant graph neural network designed to predict both interatomic potentials and tight-binding (TB) Hamiltonians for an atomic structure. The UEIPNet is trained using density functional theory calculations followed by Wannier projection to predict energies and forces as node-level targets and Wannier-projected TB matrices as edge-level targets. This enables physically consistent modeling of coupled mechanical electronic responses with near-DFT accuracy. Trained on bilayer graphene and monolayer MoS2 DFT data, UEIPNet captures key deformation-electronic effects: in twisted bilayer graphene, it reveals how interlayer spacing, in-plane strain, and out-of-plane corrugation drive isolated flat-band formation, and further shows that modulating substrate interaction strength can generate flat bands even away from the magic angle. For monolayer MoS2, the UEIPNet accurately reproduces phonon dispersions, strain-dependent band-gap evolution, and local density of states modulations under non-uniform strain. The UEIPNet offers a generalized, efficient, and scalable framework for studying deformation-electronic coupling in large-scale atomistic systems, bridging classical atomistic simulations and electronic-structure calculations.

Citations

• Elastic plate basis for the deformation and electron diffraction of twisted bilayer graphene on a substrate
• Registry-dependent potential energy and lattice corrugation of twisted bilayer graphene from quantum Monte Carlo
• e3nn: Euclidean Neural Networks
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
• Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
• Tunable band gaps and optical absorption properties of bent MoS₂ nanoribbons
• E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
• Graphene bilayers with a twist
• Advanced capabilities for materials modelling with Q uantum ESPRESSO
• A Review on Mechanics and Mechanical Properties of 2D Materials - Graphene and Beyond

Related

• Learning the Electronic Hamiltonian of Large Atomic Structures
• Equivariant graph neural network surrogates for predicting the properties of relaxed atomic configurations
• Bridging deep learning force fields and electronic structures with a physics-informed approach
• Embedding material graphs using the electron-ion potential: application to material fracture
• Efficient and Accurate Machine Learning Interatomic Potential for Graphene: Capturing Stress-Strain and Vibrational Properties