Profile approach for recognition of three-dimensional magnetic structures

Abstract

We propose an approach for low-dimensional visualisation and classification of complex topological magnetic structures formed in magnetic materials. Within the approach one converts a three-dimensional magnetic configuration to a vector containing the only components of the spins that are parallel to the z axis. The next crucial step is to sort the vector elements in ascending or descending order. Having visualized profiles of the sorted spin vectors one can distinguish configurations belonging to different phases even with the same total magnetization. For instance, spin spiral and paramagnetic states with zero total magnetic moment can be easily identified. Being combined with a simplest neural network our profile approach provides a very accurate phase classification for three-dimensional magnets characterized by complex multispiral states even in the critical areas close to phases transitions. By the example of the skyrmionic configurations we show that profile approach can be used to separate the states belonging to the same phase.

References in corpus (14)

• Scikit-learn: Machine Learning in Python
• Machine learning phases of matter
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Learning phase transitions by confusion
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• New type of stable particle like states in chiral magnets (Chiral bobbers)
• Machine learning vortices at the Kosterlitz-Thouless transition
• Three-dimensional skyrmion states in thin films of cubic helimagnets
• New spiral state and skyrmion lattice in 3D model of chiral magnets
• Parameter diagnostics of phases and phase transition learning by neural networks
• Zero-temperature phases for chiral magnets in three dimensions
• Supervised learning magnetic skyrmion phases
• Identifying structural changes with unsupervised machine learning methods

Cited by in corpus (8)

• Probing the topology of the quantum analog of a classical skyrmion
• Finding hidden order in spin models with persistent homology
• Estimating Patterns of Classical and Quantum Skyrmion States
• Reconstruction of classical skyrmions from Anderson towers: quantum Darwinism in action
• Learning Order Parameters from Videos of Dynamical Phases for Skyrmions with Neural Networks
• Recurrent network classifier for ultrafast skyrmion dynamics
• Spin wave excitations of magnetic metalorganic materials
• Benchmarking a boson sampler with Hamming nets