发表机构
Key Laboratory of Computational Physical Sciences (Ministry of Education), Institute of Computational Physical Sciences, State Key Laboratory of Surface Physics, and Department of Physics, Fudan University（复旦大学计算物理科学教育部重点实验室、计算物理科学研究所、表面物理国家重点实验室和物理系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出HamGNN-NEGF框架，利用E(3)等变图神经网络预测哈密顿量，实现线性标度量子输运模拟，在保持DFT精度的同时加速超三个数量级，并支持超过万原子器件的预测。
AI 中文摘要
将密度泛函理论（DFT）与非平衡格林函数形式（DFT-NEGF）相结合的量子输运模拟对现代技术至关重要，然而其不利的标度长期以来将预测性模拟限制在远低于实际器件万原子尺度的小型理想化系统中。在此，我们提出了HamGNN-NEGF，一个具有DFT级保真度的线性标度框架。一个在小型结构的常规DFT哈密顿量上训练的E(3)等变图神经网络预测大型器件的哈密顿量，避免了昂贵的DFT-NEGF训练数据。预测的哈密顿量与DFT导出的电极自能、用于费米能级确定的非正交核多项式方法以及递归格林函数算法集成，在固定横截面上计算成本随器件长度线性标度。即使对于包含少于500个原子的器件，HamGNN-NEGF相比完全自洽的DFT-NEGF实现了超过三个数量级的加速，且优势随系统尺寸增大而进一步增加。在纯净Pt-Si-Pt、掺杂Pt-Si:P-Pt和Pt-分子-Pt结上的基准测试证明了meV级的哈密顿量精度、忠实的透射谱以及超过10,000个原子的预测性模拟。消除输运自洽性还使得如HSE06等混合泛函无需额外的NEGF开销即可使用，而零偏压哈密顿量近似将该框架扩展到弱非线性区的有限偏压输运。因此，HamGNN-NEGF弥合了第一性原理精度与器件级模拟之间的差距，为实际纳米电子和量子器件的预测性建模提供了一条实用途径。
英文摘要
Quantum transport simulations that combine density functional theory (DFT) with the nonequilibrium Green's function formalism (DFT-NEGF) are important to modern technology, yet their unfavorable scaling has long confined predictive simulations to small, idealized systems far below the ten-thousand-atom scale of realistic devices. Here, we introduce HamGNN-NEGF, a linear-scaling framework with DFT-level fidelity. An E(3)-equivariant graph neural network trained on conventional DFT Hamiltonians of small structures predicts Hamiltonians for large devices, avoiding costly DFT-NEGF training data. The predicted Hamiltonians are integrated with DFT-derived electrode self-energies, a nonorthogonal kernel polynomial method for Fermi-level determination, and a recursive Green's function algorithm, yielding a computational cost that scales linearly with device length at fixed cross section. Even for devices containing fewer than 500 atoms, HamGNN-NEGF achieves speedups exceeding three orders of magnitude over fully self-consistent DFT-NEGF, with the advantage increasing further with system size. Benchmarks on pristine Pt-Si-Pt, doped Pt-Si:P-Pt, and Pt-molecule-Pt junctions demonstrate meV-level Hamiltonian accuracy, faithful transmission spectra, and predictive simulations beyond 10,000 atoms. Eliminating transport self-consistency also enables hybrid functionals such as HSE06 without additional NEGF overhead, while a zero-bias Hamiltonian approximation extends the framework to finite-bias transport in weakly nonlinear regimes. HamGNN-NEGF thus bridges first-principles accuracy and device-scale simulation, providing a practical route toward predictive modeling of realistic nanoelectronic and quantum devices.
Comments22 pages, 4 figures
