Machine-learning force-field models for dynamical simulations of metallic magnets

Abstract

We review recent advances in machine learning (ML) force-field methods for Landau-Lifshitz-Gilbert (LLG) simulations of itinerant electron magnets, focusing on scalability and transferability. Built on the principle of locality, a deep neural network model is developed to efficiently and accurately predict the electron-mediated forces governing spin dynamics. Symmetry-aware descriptors constructed through a group-theoretical approach ensure rigorous incorporation of both lattice and spin-rotation symmetries. The framework is demonstrated using the prototypical s-d exchange model widely employed in spintronics. ML-enabled large-scale simulations reveal novel nonequilibrium phenomena, including anomalous coarsening of tetrahedral spin order on the triangular lattice and the freezing of phase separation dynamics in lightly hole-doped, strong-coupling square-lattice systems. These results establish ML force-field frameworks as scalable, accurate, and versatile tools for modeling nonequilibrium spin dynamics in itinerant magnets.

9 pages, 5 figures

References in corpus (35)

• Skyrmion Lattice in a Chiral Magnet
• Colossal Magnetoresistant Materials: The Key Role of Phase Separation
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Spontaneous Skyrmion Ground States in Magnetic Metals
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Complexity in Strongly Correlated Electronic Systems
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• The Kernel Polynomial Method
• Big Data of Materials Science - Critical Role of the Descriptor
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Nearsightedness of Electronic Matter
• Scalar spin chirality and quantum Hall effect on a triangular lattice
• Unified Representation of Molecules and Crystals for Machine Learning
• Atomic-scale images of charge ordering in a mixed-valence manganite
• Stability of spontaneous quantum Hall state in the Triangular Kondo-lattice model
• Efficient Langevin Simulation of Coupled Classical Fields and Fermions
• Noncoplanar magnetic ordering driven by itinerant electrons on the pyrochlore lattice
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Incommensurate spiral order from double exchange interactions
• Machine learning for molecular dynamics with strongly correlated electrons
• Gradient-based stochastic estimation of the density matrix
• Spontaneous quantum Hall effect via thermally induced quadratic Fermi point
• Arrested phase separation in double-exchange models: machine-learning enabled large-scale simulation
• Machine learning electron correlation in a disordered medium
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• Convolutional neural networks for large-scale dynamical modeling of itinerant magnets
• Anomalous phase separation dynamics in a correlated electron system: machine-learning enabled large-scale kinetic Monte Carlo simulations
• Machine learning for phase ordering dynamics of charge density waves
• Machine learning predictions for local electronic properties of disordered correlated electron systems
• Kinetics of orbital ordering in cooperative Jahn-Teller models: Machine-learning enabled large-scale simulations