Abstract and research overview
Paper record · Original source linked above
This published work combines machine-learned tight-binding Hamiltonians with nonequilibrium Green’s-function transport calculations. The study benchmarks DeePTB-NEGF in two demanding settings: more than 10,000 break-junction configurations for conductance statistics, and carbon-nanotube field-effect transistors modeled at experimental dimensions with electrostatic gating. A 41 nm CNT-FET case is compared with measured transfer characteristics, and a 180 nm CNT is studied for zero-bias transmission. The paper reports major speedups for these test systems; the results are not a universal guarantee for every geometry or device.
Background on the underlying DeePTB method.
Citation: Zou, Jijie, et al. “Deep learning accelerated quantum transport simulations in nanoelectronics: from break junctions to field-effect transistors.” npj Computational Materials 11, 375 (2025).
Note: This page is an independently written overview, not a verbatim reproduction of the publisher’s abstract.
This page is part of the author's maintained research bibliography. The text may be an author-written overview or an abstract from an earlier manuscript version; consult the linked publisher or preprint for the version of record.
Citation
Jijie Zou, Zhanghao Zhouyin, Dongying Lin, Yike Huang, Linfeng Zhang, Shimin Hou, and Qiangqiang Gu. "Deep learning accelerated quantum transport simulations in nanoelectronics: from break junctions to field-effect transistors." npj Computational Materials 11, 375 (2025).