Predicting magnetic edge behaviour in graphene using neural networks
arXiv:2204.13724 · doi:10.1103/PhysRevB.106.L081411
Abstract
Magnetic moments near zigzag edges in graphene allow complex nanostructures with customised spin properties to be realised. However, computational costs restrict theoretical investigations to small or perfectly periodic structures. Here we demonstrate that a machine-learning approach, using only geometric input, can accurately estimate magnetic moment profiles, allowing arbitrarily large and disordered systems to be quickly simulated. Excellent agreement is found with mean-field Hubbard calculations, and important electronic, magnetic and transport properties are reproduced using the estimated profiles. This approach allows the magnetic moments of experimental-scale systems to be quickly and accurately predicted, and will speed-up the identification of promising geometries for spintronic applications. While machine-learning approaches to many-body interactions have largely been limited to exact solutions of complex models at very small scales, this work establishes that they can be successfully applied at very large scales at mean-field levels of accuracy.
arXiv commentsubmitted
References in corpus (39)
- Energy Band Gap Engineering of Graphene Nanoribbons
- Energy Gaps in Graphene Nanoribbons
- Half-Metallic Graphene Nanoribbons
- Graphene Spintronics
- On-surface synthesis of graphene nanoribbons with zigzag edge topology
- Machine learning phases of matter
- Emergence of magnetism in graphene materials and nanostructures
- Magnetism in graphene nano-islands
- Room temperature magnetic order on zigzag edges of narrow graphene nanoribbons
- Spatially Resolving Spin-split Edge States of Chiral Graphene Nanoribbons
- Exceptional ballistic transport in epitaxial graphene nanoribbons
- Vacancy induced magnetism in graphene and graphene ribbons
- Improvements on non-equilibrium and transport Green function techniques: the next-generation transiesta
- Conductance quantization and transport gap in disordered graphene nanoribbons
- Spin currents in rough graphene nanoribbons: Universal fluctuations and spin injection
- Topological Frustration in Graphene Nanoflakes: Magnetic Order and Spin Logic Devices
- Machine Learning Topological States
- Stability of edge states and edge magnetism in graphene nanoribbons
- Suppression of spin-polarization in graphene nanoribbon by edge defect and impurity
- Robustness of edge states in graphene quantum dots
- Quantized conductance of a suspended graphene nanoconstriction
- Dual Spin Filter Effect in a Zigzag Graphene Nanoribbon
- Theory of Magnetic Edge States in Chiral Graphene Nanoribbons
- Solving the Bose-Hubbard model with machine learning
- Electronic properties of gated triangular graphene quantum dots: Magnetism, correlations, and geometrical effects
- A spin-filter device based on armchair graphene nanoribbons
- Edge State Magnetism of Single Layer Graphene Nanostructures
- Magnetic Graphene Nanohole Superlattices
- Coupled spin states in armchair graphene nanoribbons with asymmetric zigzag edge extensions
- Size quantization of Dirac fermions in graphene constrictions
- Modeling Electronic Quantum Transport with Machine Learning
- Topology Classification from Chiral Symmetry: Chiral Phase Index and Spin Correlations in Graphene Nanoribbons
- Machine learning density functional theory for the Hubbard model
- Edge Disorder in Bottom-Up Zigzag Graphene Nanoribbons: Implications for Magnetism and Quantum Electronic Transport
- Nanostructured graphene for spintronics
- Valley notch filter in a graphene strain superlattice: Green's function and machine learning approach
- Inverse Design of a Graphene-Based Quantum Transducer via Neuroevolution
- Charge and Spin Transport Anisotropy in Nanopatterned Graphene
- Deep learning of deformation-dependent conductance in thin films: nanobubbles in graphene