Complex Spin Hamiltonian Represented by Artificial Neural Network

TL;DR

This paper introduces a machine learning approach using artificial neural networks to model complex spin Hamiltonians, enabling accurate simulation of magnetic systems like itinerant magnets and advancing the study of magnetic phenomena.

Contribution

The paper presents a novel neural network-based method to construct effective spin Hamiltonians that include both explicit and implicit interaction terms, applicable to complex magnetic systems.

Findings

Successfully reproduces artificial models

Accurately describes itinerant magnetism in Fe3GeTe2

Enables investigation of complex magnetic phenomena

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.