Deep learning tight-binding approach for large-scale electronic simulations at finite temperatures with $ab$ $initio$ accuracy

Abstract

Simulating electronic behavior in materials and devices with realistic large system sizes remains a formidable task within the $ab$ $initio$ framework due to its computational intensity. Here we show DeePTB, an efficient deep learning-based tight-binding approach with $ab$ $initio$ accuracy to address this issue. By training on structural data and corresponding $ab$ $initio$ eigenvalues, the DeePTB model can efficiently predict tight-binding Hamiltonians for unseen structures, enabling efficient simulations of large-size systems under external perturbations such as finite temperatures and strain. This capability is vital for semiconductor band gap engineering and materials design. When combined with molecular dynamics, DeePTB facilitates efficient and accurate finite-temperature simulations of both atomic and electronic behavior simultaneously. This is demonstrated by computing the temperature-dependent electronic properties of a gallium phosphide system with $10^6$ atoms. The availability of DeePTB bridges the gap between accuracy and scalability in electronic simulations, potentially advancing materials science and related fields by enabling large-scale electronic structure calculations.

15 pages, 8 figures

References in corpus (12)

• Band Gap Engineering with Ultralarge Biaxial Strains in Suspended Monolayer MoS2
• Improvements on non-equilibrium and transport Green function techniques: the next-generation transiesta
• Localized atomic basis set in the projector augmented wave method
• Modeling electronic structure and transport properties of graphene with resonant scattering centers
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Excitation spectrum and high energy plasmons in single- and multi-layer graphene
• Direct Method for Calculating Temperature-Dependent Transport Properties
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models
• Deep learning tight-binding approach for large-scale electronic simulations at finite temperatures with $ab$ $initio$ accuracy
• Neural network representation of electronic structure from $ab$ $initio$ molecular dynamics
• A computational method to estimate spin-orbital interaction strength in solid state systems

Cited by in corpus (4)

• Deep learning tight-binding approach for large-scale electronic simulations at finite temperatures with $ab$ $initio$ accuracy
• Crystalline Material Discovery in the Era of Artificial Intelligence
• Review of the tight-binding method applicable to the properties of moiré superlattices
• Predictive Free Energy Simulations Through Hierarchical Distillation of Quantum Hamiltonians