GPUTB-2:一种高效的E(3)网络方法用于学习高精度正交哈密顿量
GPUTB-2:An efficient E(3) network method for learning high-precision orthogonal Hamiltonian
AI总结:
GPUTB-2通过等变网络和张量积层实现高效学习高精度正交哈密顿量,适用于大规模电子结构计算。
摘要:
尽管等变神经网络已成为学习电子哈密顿量的基石,但线性组合原子轨道(LCAO)基组的内在非正交性提出了根本性的挑战。哈密顿量正交化的计算成本随着O(N^3)增长,严重阻碍了包含数万到数百万原子的大规模系统的电子结构计算。为了解决这一问题,我们开发了GPUTB-2,一种通过直接在电子能带结构上训练来隐式学习保持正交性的哈密顿量的框架。得益于由Gaunt张量积和SO(2)张量积层加速的E(3)-等变网络,GPUTB-2在多个基准系统上实现了比GPUTB更高的精度。此外,GPUTB-2能够准确预测大规模电子结构,包括受温度扰动的SnSe的输运性质以及魔角扭曲双层石墨烯的能带结构。通过进一步将该框架与线性缩放量子输运(LSQT)方法结合,我们研究了百万原子非晶石墨的电子性质,并在更复杂的非晶硅中发现了压力诱导的电子结构转变。这些结果共同确立了GPUTB-2作为一种高精度且可扩展的方法,用于预测正交哈密顿量。
英文摘要:
Although equivariant neural networks have become a cornerstone for learning electronic Hamiltonians, the intrinsic non-orthogonality of linear combinations of atomic orbitals (LCAO) basis sets poses a fundamental challenge. The computational cost of Hamiltonian orthogonalization scales as O(N^3), which severely hinders electronic structure calculations for large-scale systems containing hundreds of thousands to millions of atoms. To address this issue, we develop GPUTB-2, a framework that learns implicitly orthogonality-preserving Hamiltonians by training directly on electronic band structures. Benefiting from an E(3)-equivariant network accelerated by Gaunt tensor product and SO(2) tensor product layers, GPUTB-2 achieves significantly higher accuracy than GPUTB across multiple benchmark systems. Moreover, GPUTB-2 accurately predicts large-scale electronic structures, including transport properties of temperature-perturbed SnSe and the band structures of magic-angle twisted bilayer graphene. By further integrating this framework with the linear-scaling quantum transport (LSQT) method, we investigate the electronic properties of million-atom amorphous graphene and uncover pressure-induced electronic structure transitions in more complex amorphous silicon. Together, these results establish GPUTB-2 as a high-accuracy and scalable approach for predicting orthogonal Hamiltonians.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。