Smooth Overlap of Spin Orientations: Machine Learning Exchange Fields for Ab-initio Spin Dynamics

Abstract

We add the magnetic degrees of freedom to the widely used Gaussian Approximation Potential of machine learning (ML) and present a model that describes the potential energy surface of a crystal based on the atomic coordinates as well as their noncollinear magnetic moments. Assuming an adiabatic approximation for the spin directions and magnitudes, the ML model depends solely on spin coordinates and orientation, resulting in computational efffciency and enabling ab initio spin dynamics. Leveraging rotational symmetries of magnetic interactions, the ML model can incorporate various magnetic interactions, expanding into two-body, three-body terms, etc., following the spirit of cluster expansion. For simplicity, we implement the ML model with a two-body form for the exchange interaction. Comparing total energies and local fields predicted by the model for noncollinear spin arrangements with explicit results of constrained noncollinear density functional calculations for bcc Fe yields excellent results, within 1 meV/spin for the total energy. Further optimization, including three-body and other terms, is expected to encompass diverse magnetic interactions and enhance the model's accuracy. This will extend the model's applicability to a wide range of materials and facilitate the machine learning ab initio spin dynamics.

16 pages, 7 figures

References in corpus (35)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Magnetic 2D materials and heterostructures
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Nonlocal magnetization dynamics in ferromagnetic heterostructures
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• On-the-fly machine learning force field generation: Application to melting points
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• Ab-initio calculations of exchange interactions, spin-wave stiffness constants, and Curie temperatures of Fe, Co, and Ni
• A method for atomistic spin dynamics simulations: implementation and examples
• Significant Dzyaloshinskii-Moriya Interaction at Graphene-Ferromagnet Interfaces due to Rashba-effect
• Giant room temperature interface spin Hall and inverse spin Hall effects
• Interface enhancement of Gilbert damping from first-principles
• On the Completeness of Atomic Structure Representations
• Atomic cluster expansion of scalar, vectorial and tensorial properties and including magnetism and charge transfer
• Disorder Dependence of Interface Spin Memory Loss
• First-principles calculations of magnetization relaxation in pure Fe, Co, and Ni with frozen thermal lattice disorder
• Direct Method for Calculating Temperature-Dependent Transport Properties
• Deep-learning electronic-structure calculation of magnetic superstructures
• Interatomic exchange coupling of BCC iron
• Spin-Dependent Graph Neural Network Potential for Magnetic Materials
• Anharmonic lattice dynamics in large thermodynamic ensembles with machine-learning force fields: CsPbBr${}_3$ a phonon-liquid with Cs rattlers
• A spectral-neighbour representation for vector fields: machine-learning potentials including spin
• Theory of non-collinear interactions beyond Heisenberg exchange; applications to bcc Fe
• Arrested phase separation in double-exchange models: machine-learning enabled large-scale simulation
• Spin-flip diffusion length in 5d transition metal elements: a first-principles benchmark
• Complex Spin Hamiltonian Represented by Artificial Neural Network
• Plane wave implementation of the magnetic force theorem for magnetic exchange constants: Application to bulk Fe, Co and Ni
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• Searching for iron nanoparticles with a general-purpose Gaussian approximation potential
• A theoretical perspective on the modification of the magnetocrystalline anisotropy at molecule-cobalt interfaces
• Temperature dependence of side-jump spin Hall conductivity
• Phase transitions of LaMnO${}_3$ and SrRuO${}_3$ from DFT + U based machine learning force fields simulations
• Fitting to magnetic forces improves the reliability of magnetic Moment Tensor Potentials
• High-performance descriptor for magnetic materials: Accurate discrimination of magnetic structure