Quantifying the magnetic interactions governing chiral spin textures using deep neural networks

Abstract

The interplay of magnetic interactions in chiral multilayer films gives rise to nanoscale topological spin textures, which form attractive elements for next-generation computing. Quantifying these interactions requires several specialized, time-consuming, and resource-intensive experimental techniques. Imaging of ambient domain configurations presents a promising avenue for high-throughput extraction of the parent magnetic interactions. Here we present a machine learning-based approach to determine the key interactions -- symmetric exchange, chiral exchange, and anisotropy -- governing chiral domain phenomenology in multilayers. Our convolutional neural network model, trained and validated on over 10,000 domain images, achieved $R^2>0.85$ in predicting the parameters and independently learned physical interdependencies between them. When applied to microscopy data acquired across samples, our model-predicted parameter trends are consistent with independent experimental measurements. These results establish ML-driven techniques as valuable, high-throughput complements to conventional determination of magnetic interactions, and serve to accelerate materials and device development for nanoscale electronics.

arXiv comment7 pages, 6 figures

References in corpus (25)

• The design and verification of Mumax3
• Machine learning and the physical sciences
• Advances in the Physics of Magnetic Skyrmions and Perspective for Technology
• Observation of room temperature magnetic skyrmions and their current-driven dynamics in ultrathin Co films
• Additive interfacial chiral interaction in multilayers for stabilization of small individual skyrmion at room temperature
• Skyrmions at room temperature : From magnetic thin films to magnetic multilayers
• Emergent Phenomena Induced by Spin-Orbit Coupling at Surfaces and Interfaces
• Tunable Room Temperature Magnetic Skyrmions in Ir/Fe/Co/Pt Multilayers
• Beyond skyrmions: Review and perspectives of alternative magnetic quasiparticles
• Magnetic skyrmion artificial synapse for neuromorphic computing
• Spectroscopic confirmation of linear relation between Heisenberg- and interfacial Dzyaloshinskii-Moriya-exchange in polycrystalline metal films
• Room-temperature current-induced generation and motion of sub-100nm skyrmions
• Asymmetric Magnetic Domain-Wall Motion by the Dzyaloshinskii-Moriya Interaction
• The 2020 Skyrmionics Roadmap
• Skyrmion Gas Manipulation for Probabilistic Computing
• Potential implementation of Reservoir Computing models based on magnetic skyrmions
• Current-Driven Skyrmion Dynamics and Drive-Dependent Skyrmion Hall Effect in an Ultrathin Film
• Supervised learning magnetic skyrmion phases
• Machine Learning Application to Two-Dimensional Dzyaloshinskii-Moriya Ferromagnets
• Determination of the Dzyaloshinskii-Moriya interaction using pattern recognition and machine learning
• Unveiling the emergent traits of chiral spin textures in magnetic multilayers
• Thermal evolution of skyrmion formation mechanism in chiral multilayer films
• Determination of the energy of the Dzyaloshinskii-Moriya interaction in [Co/Pd(111)]5 superlattices with different Co thickness by micromagnetic simulations of labyrinth domain structures
• Quantifying symmetric exchange in ultrathin ferromagnetic films with chirality
• Tailoring Zero-Field Magnetic Skyrmions in Chiral Multilayers by a Duet of Interlayer Exchange Couplings