Deep Learning-Based Quantum Transport Simulations in Two-Dimensional Materials

Two-dimensional (2D) materials exhibit a wide range of electronic properties that make them promising candidates for next-generation nanoelectronic devices. Accurate prediction of their quantum transport behavior is therefore of both fundamental and technological importance. While density functional theory (DFT) combined with the non-equilibrium Green$’$s function (NEGF) formalism provides reliable insights, its high computational cost limits applications to large-scale or high-throughput studies. Here we present DeePTB-NEGF, a framework that combines a deep learning-based tight-binding Hamiltonians derived learned directly from first-principles calculations (DeePTB) with efficient quantum transport simulations implemented in the DPNEGF package. To validate the method, we apply it to three prototypical 2D materials: graphene, hexagonal boron nitride (h-BN), and MoS$_2$. The resulting band structures and transmission spectra show excellent agreement with conventional DFT-NEGF results, while achieving orders-of-magnitude improvement in efficiency. These results highlight the capability of DeePTB-NEGF to enable accurate and efficient quantum transport simulations, thereby opening avenues for large-scale exploration and device design in 2D materials.

💡 Research Summary

The paper introduces DeePTB‑NEGF, a hybrid framework that combines deep‑learning‑derived tight‑binding (TB) Hamiltonians (DeePTB) with the non‑equilibrium Green’s function (NEGF) formalism for quantum transport simulations of two‑dimensional (2D) materials. Traditional density‑functional‑theory (DFT) combined with NEGF provides high accuracy but is computationally prohibitive for large systems or high‑throughput studies because each transport calculation requires a self‑consistent DFT evaluation of the electronic structure and the construction of electrode self‑energies. DeePTB addresses this bottleneck by training a neural network to map local atomic environments to corrections of Slater‑Koster integrals, thereby generating sparse TB Hamiltonians that retain first‑principles fidelity. Once trained, the model can instantly infer Hamiltonians for unseen structures, which are then fed into the open‑source DPNEGF package to compute retarded Green’s functions, broadening matrices, and the transmission function T(E)=Tr