Abstract
The properties of complicated magnetic domain structures induced by various spin–spin interactions in magnetic systems have been extensively investigated in recent years. To understand the statistical and dynamic properties of complex magnetic structures, it is crucial to obtain information on the effective field distribution over the structure, which is not directly provided by magnetization. In this study, we use a deep learning technique to estimate the effective fields of spin configurations. We construct a deep neural network and train it with spin configuration datasets generated by Monte Carlo simulation. We show that the trained network can successfully estimate the magnetic effective field even though we do not offer explicit Hamiltonian parameter values. The estimated effective field information is highly applicable; it is utilized to reduce noise, correct defects in the magnetization data, generate spin configurations, estimate external field responses, and interpret experimental images.
Highlights
The properties of complicated magnetic domain structures induced by various spin–spin interactions in magnetic systems have been extensively investigated in recent years
The effective field, which is a crucial concept for predicting the time evolution and stability of magnetic configurations in micromagnetic simulations, typically cannot be directly measured from microscopy techniques; the effective field can be regarded as hidden information in the spin configuration
We devised a novel method based on a deep learning technique to estimate the effective field information of spin configurations
Summary
The properties of complicated magnetic domain structures induced by various spin–spin interactions in magnetic systems have been extensively investigated in recent years. Deep learning techniques have achieved remarkable success in modeling physical data It has been intensively applied in the field of magnetism research to investigate various properties of unique magnetic domain structures appearing in low dimensions, estimate Hamiltonian parameters of magnetic complex structures from experimental observation[7,8,9] and generate ground states in various s ystems[10,11,12]. Another promising application of deep learning techniques is to reconstruct hidden or unseen information from given data. The technique has great potential to be used in Scientific Reports | (2021) 11:22937
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
