Machine Learning Application to Two-Dimensional Dzyaloshinskii-Moriya Ferromagnets

TL;DR

This paper demonstrates how machine learning, particularly convolutional neural networks, can effectively predict phases and external parameters in two-dimensional Dzyaloshinskii-Moriya ferromagnets supporting skyrmion states, including applications to experimental data.

Contribution

Introduces a new training scheme based on input features and applies CNNs to predict phases and parameters in 2D skyrmion models, extending to experimental data interpretation.

Findings

Successful phase prediction using CNNs with multiple layers.

Reliable predictions of magnetic field and temperature effects.

Effective generalization to related configurations.

Abstract

Principles of machine learning are applied to models that support skyrmion phases in two dimensions. Successful feature predictions on various phases of the skyrmion model were possible with several layers of convolutional neural network inserted together with several neural network layers. A new training scheme based on features of the input configuration such as magnetization and spin chirality is introduced. It proved possible to further train external parameters such as the magnetic field and temperature and make reliable predictions on them. Algorithms trained on only the z-component or the xy-components of the spin gave equally reliable predictions. The predictive capacity of the algorithm extended to configurations not generated by the original model, but related ones. A procedure for integrating the machine learning algorithm into the interpretation of experimental data is given.