Machine learning approach to genome of two-dimensional materials with flat electronic bands

Abstract

Many-body physics of electron-electron correlations plays a central role in condensed mater physics, it governs a wide range of phenomena, stretching from superconductivity to magnetism, and is behind numerous technological applications. To explore this rich interaction-driven physics, two-dimensional (2D) materials with flat electronic bands provide a natural playground thanks to their highly localised electrons. Currently, thousands of 2D materials with computed electronic bands are available in open science databases, awaiting such exploration. Here we used a new machine learning algorithm combining both supervised and unsupervised machine intelligence to automate the otherwise daunting task of materials search and classification, to build a genome of 2D materials hosting flat electronic bands. To this end, a feedforward artificial neural network was employed to identify 2D flat band materials, which were then classified by a bilayer unsupervised learning algorithm. Such a hybrid approach of exploring materials databases allowed us to reveal completely new material classes outside the known flat band paradigms, offering new systems for in-depth study on their electronic interactions.

References in corpus (23)

• Magic-angle graphene superlattices: a new platform for unconventional superconductivity
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Moire bands in twisted double-layer graphene
• On representing chemical environments
• Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
• AFLOW: An automatic framework for high-throughput materials discovery
• The Computational 2D Materials Database: High-Throughput Modeling and Discovery of Atomically Thin Crystals
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Quantum anomalous Hall effect from intertwined moiré bands
• Topological flat bands in frustrated kagome lattice CoSn
• Topology-Scaling Identification of Layered Solids and Stable Exfoliated 2D Materials
• Classification of flat bands according to the band-crossing singularity of Bloch wave functions
• Unsupervised machine learning and band topology
• Spin-Orbit-Induced Topological Flat Bands in Line and Split Graphs of Bipartite Lattices
• Representing individual electronic states for machine learning GW band structures of 2D materials
• Screening 2D materials with topological flat bands
• Pairing and superconductivity in the flat band: Creutz lattice
• Flat bands and Dirac cones in breathing lattices
• Perfect flat band with chirality and charge ordering out of strong spin-orbit interaction
• Haldane phase in the sawtooth lattice: Edge states, entanglement spectrum and the flat band
• Online Search Tool for Graphical Patterns in Electronic Band Structures
• Light-Induced Ferromagnetism in Moiré Superlattices
• Inventory of high-quality flat-band van der Waals materials

Cited by in corpus (5)

• Universal Machine Learning Kohn-Sham Hamiltonian for Materials
• Designing single and degenerate flat bands in the kagome lattice with long-range hopping
• Elf autoencoder: unsupervised exploration of flat-band materials using electronic band structure fingerprints
• Isolated nearly flat higher Chern band in monolayer transition metal trihalides
• Orbital homology of p and t2g orbitals in models and materials