Machine learning techniques to construct detailed phase diagrams for skyrmion systems

Abstract

Recently, there has been an increased interest in the application of machine learning (ML) techniques to a variety of problems in condensed matter physics. In this regard, of particular significance is the characterization of simple and complex phases of matter. Here, we use a ML approach to construct the full phase diagram of a well known spin model combining ferromagnetic exchange and Dzyaloshinskii-Moriya (DM) interactions where topological phases emerge. At low temperatures, the system is tuned from a spiral phase to a skyrmion crystal by a magnetic field. However, thermal fluctuations induce two types of intermediate phases, bimerons and skyrmion gas, which are not as easily determined as spirals or skyrmion crystals. We resort to large scale Monte Carlo simulations to obtain low temperature spin configurations, and train a convolutional neural network (CNN), taking only snapshots at specific values of the DM couplings, to classify between the different phases, focusing on the intermediate and intricate topological textures. We then apply the CNN to higher temperature configurations and to other DM values, to construct a detailed magnetic field-temperature phase diagram, achieving outstanding results. We discuss the importance of including the disordered paramagnetic phases in order to get the phase boundaries, and finally, we compare our approach with other ML algorithms.

arXiv comment9 pages, 10 figures; accepted for publication in Physical Review B

References in corpus (38)

• Skyrmion Lattice in a Chiral Magnet
• Advances in the Physics of Magnetic Skyrmions and Perspective for Technology
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Learning phase transitions by confusion
• Beyond skyrmions: Review and perspectives of alternative magnetic quasiparticles
• Discovering Phase Transitions with Unsupervised Learning
• Skyrmion phase and competing magnetic orders on a breathing kagome lattice
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Antiferromagnetic Half-skyrmions and Bimerons at room temperature
• Fractional antiferromagnetic skyrmion lattice induced by anisotropic couplings
• Magnetic bimerons as skyrmion analogues in in-plane magnets
• Compact Skyrmions, Merons and Bimerons in Thin Chiral Magnetic Films
• Three-sublattice Skyrmion crystal in the antiferromagnetic triangular lattice
• Imaging the coupling between itinerant electrons and localised moments in the centrosymmetric skyrmion magnet GdRu2Si2
• Machine Learning Assisted Insight to Spin Ice Dy${}_2$Ti${}_2$O${}_7$
• Supervised learning magnetic skyrmion phases
• A Kagome Map of Spin Liquids: from XXZ to Dzyaloshinskii-Moriya Ferromagnet
• Generic nearest-neighbour kagome model: XYZ & Dzyaloshinskii-Moriya, and comparison to pyrochlore
• Field-driven metamorphoses of isolated skyrmions within the conical state of cubic helimagnets
• Machine Learning Application to Two-Dimensional Dzyaloshinskii-Moriya Ferromagnets
• Revealing the Phase Diagram of Kitaev Materials by Machine Learning: Cooperation and Competition between Spin Liquids
• Determination of the Dzyaloshinskii-Moriya interaction using pattern recognition and machine learning
• Field-induced pseudo-skyrmion phase in the antiferromagnetic kagome lattice
• Field induced multiple order-by-disorder state selection in antiferromagnetic honeycomb bilayer lattice
• Bimeron nanoconfined design
• Identification of hidden order and emergent constraints in frustrated magnets using tensorial kernel methods
• Stability of skyrmion crystal phase in antiferromagnetic triangular lattice with DMI and single-ion anisotropy
• Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets
• Engineering antiferromagnetic skyrmions and antiskyrmions at metallic interfaces
• Formation and growth of skyrmion crystal phase in a frustrated Heisenberg antiferromagnet with Dzyaloshinskii-Moriya interaction
• Degenerate and chiral states in the extended Heisenberg model in the kagome lattice
• Learning Order Parameters from Videos of Dynamical Phases for Skyrmions with Neural Networks
• Recurrent network classifier for ultrafast skyrmion dynamics
• Antiskyrmions and Bloch Skyrmions in Magnetic Dresselhaus Metals
• Integration of Machine Learning with Neutron Scattering: Hamiltonian Tuning in Spin Ice with Pressure
• Inferring Hidden Symmetries of Exotic Magnets from Detecting Explicit Order Parameters
• Topological characterization of dynamic chiral magnetic textures using machine learning

Cited by in corpus (5)

• Estimating Patterns of Classical and Quantum Skyrmion States
• Machine learning for structure-property relationships: Scalability and limitations
• Identifying magnetic antiskyrmions while they form with convolutional neural networks
• Interplay of electric and magnetic fields in skyrmion phases of the classical Heisenberg model on a square lattice
• Predicting parameters of a model cuprate superconductor using machine learning