Data-Driven Estimation of the interfacial Dzyaloshinskii-Moriya Interaction with Machine Learning

2026-03-28

AI Summary

Accurately quantifying the interfacial Dzyaloshinskii–Moriya interaction (DMI) strength in magnetic materials has long been hindered by inconsistencies among indirect experimental approaches. This work proposes a convolutional neural network–based method that directly infers DMI strength from magnetic bubble domain textures in simulated magneto-optical Kerr effect images, circumventing reliance on conventional indirect techniques. The approach demonstrates for the first time that DMI values can be predicted with high accuracy and reliability solely from bubble structures, exhibiting strong generalization even beyond the training range. Trained on micromagnetic simulation data incorporating structural inhomogeneities, additive noise, and pixelation effects, the compact network architecture proves highly robust against noise, sample non-uniformity, and low spatial resolution, enabling rapid and quantitative DMI determination.

Abstract

Machine learning offers powerful tools to support experimental techniques, particularly for extracting latent features from large datasets. In magnetic materials, accurately estimating the interfacial Dzyaloshinskii-Moriya interaction strength remains challenging, as existing experimental methods often rely on indirect measurements and can yield inconsistent results across techniques. Because this interaction is often extracted experimentally from bubble domain expansion, we investigate whether bubble textures alone contain sufficient and reliable information for data driven DMI inference. We therefore develop a compact convolutional neural network trained on a comprehensive micromagnetic dataset of magnetic bubble domains designed to emulate magneto optical Kerr effect imaging, including structural non uniformity, additive noise, and image pixelation. The proposed network demonstrates strong robustness against sample inhomogeneities, noise, and reduced spatial resolution. Furthermore, it exhibits reliable generalization by accurately predicting DMI values outside the trained interval. These results support the use of machine learning as a fast and quantitative tool to characterize magnetic textures with interfacial DMI.

Problem

• Dzyaloshinskii-Moriya interaction
• magnetic materials
• interfacial DMI
• bubble domain
• experimental estimation

Innovation

• machine learning
• Dzyaloshinskii-Moriya interaction
• magnetic bubble domains
• convolutional neural network
• data-driven characterization