Complex Spin Hamiltonian Represented by Artificial Neural Network

Abstract

The effective spin Hamiltonian method is widely adopted to simulate and understand the behavior of magnetism. However, the magnetic interactions of some systems, such as itinerant magnets, are too complex to be described by any explicit function, which prevents an accurate description of magnetism in such systems. Here, we put forward a machine learning (ML) approach, applying an artificial neural network (ANN) and a local spin descriptor to develop effective spin potentials for any form of interaction. The constructed Hamiltonians include an explicit Heisenberg part and an implicit non-linear ANN part. Such a method successfully reproduces artificially constructed models and also sufficiently describe the itinerant magnetism of bulk Fe3GeTe2. Our work paves a new way for investigating complex magnetic phenomena (e.g., skyrmions) of magnetic materials.

14 pages, 3 figures

References in corpus (6)

• Spontaneous Skyrmion Ground States in Magnetic Metals
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Possible Kitaev Quantum Spin Liquid State in 2D Materials with S=3/2
• Giant Biquadratic Exchange in 2D Magnets and its Role in Stabilizing Ferromagnetism of NiCl2 Monolayer
• Deep learning inter-atomic potential model for accurate irradiation damage simulations

Cited by in corpus (7)

• A practical guide to machine learning interatomic potentials -- Status and future
• Spin-Dependent Graph Neural Network Potential for Magnetic Materials
• Tuning the magnetic interactions in van der Waals Fe${}_3$GeTe${}_2$ heterostructures: A comparative study of \textit{ab initio} methods
• General time-reversal equivariant neural network potential for magnetic materials
• A Self-Adaptive First-Principles Approach for Magnetic Excited States
• Classification of magnetic order from electronic structure by using machine learning
• Smooth Overlap of Spin Orientations: Machine Learning Exchange Fields for Ab-initio Spin Dynamics