Deep-learning electronic-structure calculation of magnetic superstructures

Abstract

Ab initio study of magnetic superstructures (e.g., magnetic skyrmion) is indispensable to the research of novel materials but bottlenecked by its formidable computational cost. For solving the bottleneck problem, we develop a deep equivariant neural network method (named xDeepH) to represent density functional theory Hamiltonian $H_{\text{DFT}}$ as a function of atomic and magnetic structures and apply neural networks for efficient electronic structure calculation. Intelligence of neural networks is optimized by incorporating a priori knowledge about the important locality and symmetry properties into the method. Particularly, we design a neural-network architecture fully preserving all equivalent requirements on $H_{\text{DFT}}$ by the Euclidean and time-reversal symmetries ($E(3)\times \{I,T\}$), which is essential to improve method performance. High accuracy (sub-meV error) and good transferability of xDeepH are shown by systematic experiments on nanotube, spin-spiral, and Moiré magnets, and the capability of studying magnetic skyrmion is also demonstrated. The method could find promising applications in magnetic materials research and inspire development of deep-learning ab initio methods.

References in corpus (16)

• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Machine Learning Force Fields
• Nearsightedness of Electronic Matter
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Spontaneous skyrmionic lattice from anisotropic symmetric exchange in a Ni-halide monolayer
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
• Curved Magnetism in CrI${}_3$
• Magnetic skyrmion lattices in a novel two-dimensional twisted bilayer magnet
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
• Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
• Deep Density: circumventing the Kohn-Sham equations via symmetry preserving neural networks

Cited by in corpus (13)

• AI-driven inverse design of materials: Past, present and future
• Deep-learning density functional perturbation theory
• Universal materials model of deep-learning density functional theory Hamiltonian
• An equivariant graph neural network for the elasticity tensors of all seven crystal systems
• Neural-network Density Functional Theory Based on Variational Energy Minimization
• InvDesFlow-AL: active learning-based workflow for inverse design of functional materials
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Roadmap on Quantum Magnetic Materials
• Review of the tight-binding method applicable to the properties of moiré superlattices
• Moiré spintronics: Emergent phenomena, material realization and machine learning accelerating discovery
• Electronic structures of crystalline and amorphous GeSe and GeSbTe compounds using machine learning empirical pseudopotentials
• Fault-tolerant Quantum Chemical Calculations with Improved Machine-Learning Models
• Smooth Overlap of Spin Orientations: Machine Learning Exchange Fields for Ab-initio Spin Dynamics