Identifying magnetic antiskyrmions while they form with convolutional neural networks

TL;DR

This paper demonstrates how convolutional neural networks can effectively identify and classify various topological magnetic phases, including skyrmions and bimerons, in chiral magnets from simulation data, enabling faster analysis and potential real-world applications.

Contribution

The study introduces a multi-label CNN framework capable of early and reliable identification of magnetic phases and features in chiral magnets, improving upon traditional analysis methods.

Findings

CNN accurately classifies magnetic phases from simulation snapshots.

The model predicts phases early in the formation process.

Approach applicable to real-world magnetic images.

Abstract

Chiral magnets have attracted a large amount of research interest in recent years because they support a variety of topological defects, such as skyrmions and bimerons, and allow for their observation and manipulation through several techniques. They also have a wide range of applications in the field of spintronics, particularly in developing new technologies for memory storage devices. However, the vast amount of data generated in these experimental and theoretical studies requires adequate tools, among which machine learning is crucial. We use a Convolutional Neural Network (CNN) to identify the relevant features in the thermodynamical phases of chiral magnets, including (anti-)skyrmions, bimerons, and helical and ferromagnetic states. We use a flexible multi-label classification framework that can correctly classify states in which different features and phases are mixed. We then train the CNN to predict the features of the final state from snapshots of intermediate states of a lattice Monte Carlo simulation. The trained model allows identifying the different phases reliably and early in the formation process. Thus, the CNN can significantly speed up the large-scale simulations for 3D materials that have been the bottleneck for quantitative studies so far. Moreover, this approach can be applied to the identification of mixed states and emerging features in real-world images of chiral magnets.