Machine learning dynamics of phase separation in correlated electron magnets

TL;DR

This paper introduces a machine learning approach to efficiently simulate large-scale electronic phase separation in correlated electron magnets, enabling detailed dynamical studies of complex magnetic phenomena.

Contribution

It develops neural network-based models for linear-scaling exchange field calculations, facilitating large-scale Landau-Lifshitz dynamics simulations of the ferromagnetic Kondo lattice model.

Findings

Neural networks accurately reproduce exchange forces from small lattice datasets.

Simulations match exact results for relaxation processes and correlation functions.

Method enables large-scale, efficient dynamical simulations of correlated electron systems.

Abstract

We demonstrate machine-learning enabled large-scale dynamical simulations of electronic phase separation in double-exchange system. This model, also known as the ferromagnetic Kondo lattice model, is believed to be relevant for the colossal magnetoresistance phenomenon. Real-space simulations of such inhomogeneous states with exchange forces computed from the electron Hamiltonian can be prohibitively expensive for large systems. Here we show that linear-scaling exchange field computation can be achieved using neural networks trained by datasets from exact calculation on small lattices. Our Landau-Lifshitz dynamics simulations based on machine-learning potentials nicely reproduce not only the nonequilibrium relaxation process, but also correlation functions that agree quantitatively with exact simulations. Our work paves the way for large-scale dynamical simulations of correlated electron systems using machine-learning models.