A deep learning approach to search for superconductors from electronic bands
arXiv:2409.07721 · doi:10.1088/3050-287X/adf6cb
Abstract
Energy band theory is a foundational framework in condensed matter physics. In this work, we employ a deep learning method, BNAS, to find a direct correlation between electronic band structure and superconducting transition temperature. Our findings suggest that electronic band structures can act as primary indicators of superconductivity. To avoid overfitting, we utilize a relatively simple deep learning neural network model, which, despite its simplicity, demonstrates predictive capabilities for superconducting properties. By leveraging the attention mechanism within deep learning, we are able to identify specific regions of the electronic band structure most correlated with superconductivity. This novel approach provides new insights into the mechanisms driving superconductivity from an alternative perspective. Moreover, we predict several potential superconductors that may serve as candidates for future experimental synthesis.
References in corpus (27)
- Superconductivity at 250 K in lanthanum hydride under high pressures
- Superconductivity in Iron Compounds
- Electron-phonon interactions from first principles
- Superconductivity near 80 Kelvin in single crystals of La3Ni2O7 under pressure
- Nonlinear lattice dynamics as a basis for enhanced superconductivity in YBa2Cu3O6.5
- Phonon dispersion and electron-phonon coupling in MgB_2 and AlB_2
- Observation of superconductivity at 30 K~46 K in AxFe2Se2 (A = Li, Na, Ba, Sr, Ca, Yb, and Eu)
- Bilayer two-orbital model of LaNiO under pressure
- Proximity of antiferromagnetism and superconductivity in LaOFFeAs: effective Hamiltonian from ab initio studies
- CePt3Si: an unconventional superconductor without inversion center
- Theoretical evidence for strong correlations and incoherent metallic state in FeSe
- Spin fluctuations and superconductivity in a 3D tight-binding model for BaFe2As2
- Pressure dependence of the magic twist angle in graphene superlattices
- d+id' Chiral Superconductivity in Bilayer Silicene
- Superconductivity under high pressure in LaFeAsO
- Deep Learning Model for Finding New Superconductors
- Functional Form of the Superconducting Critical Temperature from Machine Learning
- Effect of the chemical pressure on superconductivity and SDW in undoped and 15%F doped La1-yYyFeAsO compounds
- Electronic structure, magnetism and high-temperature superconductivity in the multi-layer octagraphene and octagraphite
- Machine learning the relationship between Debye temperature and superconducting transition temperature
- Superconductivity up to 14.2 K in MnB under pressure
- Linear Magnetoresistance and Type-I Superconductivity in -IrSn
- Superband: an Electronic-band and Fermi surface structure database of superconductors
- Diluted Yu-Shiba-Rusinov arrays on the -BiPd anisotropic superconductor
- Discovery of High-Temperature Superconducting Ternary Hydrides via Deep Learning
- Pressure-induced superconductivity in monoclinic RhBi
- Superconductivity in pressurized ReMoB