journal article·2025-06-11

Atom Identification in Bilayer Moiré Materials with Gomb-Net

Austin C. Houston, Sumner B. Harris, Hao Wang, Yu-Chuan Lin, David B. Geohegan, Kai Xiao, Gerd Duscher

Nano Letters· Volume 25· Issue 23
Publisher page

Abstract

Moiré patterns in van der Waals bilayer materials complicate the analysis of atomic-resolution images, hindering the atomic-scale insight typically attainable with scanning transmission electron microscopy. Here, we report a method to detect the positions and identities of atoms in each of the individual layers that compose twisted bilayer heterostructures. We developed a deep learning model, Gomb-Net, which identifies the coordinates and atomic species in each layer, deconvoluting the moiré pattern. This enables layer-specific mapping of atomic positions and dopant distributions, unlike other commonly used segmentation models which struggle with moiré-induced complexity. Using this approach, we explored the Se atom substitutional site distribution in a twisted fractional Janus WS 2 -WS 2(1– x ) Se 2 x heterostructure and found that layer-specific implantation sites are unaffected by the moiré pattern’s local energetic or electronic modulation. This advancement enables atom identification within material regimes where it was not possible before, opening new insights into previously inaccessible material physics.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Electronic and Structural Properties of Oxides · Machine Learning in Materials Science · 2D Materials and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Materials Science and Engineering

The University of Tennessee

Center for Nanophase Materials Sciences

Oak Ridge National Laboratory

Min H. Kao Department of Electrical Engineering and Computer Science

National Yang Ming Chiao Tung University

Funding

Oak Ridge National Laboratory · National Institute of Standards and Technology · Basic Energy Sciences · University of Tennessee, Knoxville

References (36)

Show source-provided references
1. 10.1038/s41567-020-01154-310.1038/s41567-020-01154-3 ↗
2. 10.1038/s41578-024-00682-110.1038/s41578-024-00682-1 ↗
3. 10.1126/sciadv.170169610.1126/sciadv.1701696 ↗
4. 10.1073/pnas.110817410810.1073/pnas.1108174108 ↗
5. Schwartz L. H. · 2013
6. 10.1093/jmicro/50.3.22710.1093/jmicro/50.3.227 ↗
7. 10.1016/0304-3991(94)00173-K10.1016/0304-3991(94)00173-K ↗
8. 10.1016/S0304-3991(02)00249-810.1016/S0304-3991(02)00249-8 ↗
9. 10.1016/0304-3991(96)00020-410.1016/0304-3991(96)00020-4 ↗
10. 10.1109/TSMC.1979.431007610.1109/TSMC.1979.4310076 ↗
11. Boykov, Y. Y.; Jolly, M.P. Interactive graph cuts for optimal boundary & region segmentation of objects in ND images. In Proceedings of the Eighth IEEE International Conference on Computer Vision; IEEE, 2001; pp 105–112.10.1109/ICCV.2001.937505 ↗
12. 10.1007/BF0013357010.1007/BF00133570 ↗
13. 10.1038/s42256-022-00555-810.1038/s42256-022-00555-8 ↗
14. 10.1038/s41598-021-84499-w10.1038/s41598-021-84499-w ↗
15. 10.1038/s43586-022-00095-w10.1038/s43586-022-00095-w ↗
16. 10.1021/acs.nanolett.0c0026910.1021/acs.nanolett.0c00269 ↗
17. 10.1021/acsnano.7b0750410.1021/acsnano.7b07504 ↗
18. 10.1021/acs.nanolett.3c0189210.1021/acs.nanolett.3c01892 ↗
19. 10.1038/s41524-018-0086-710.1038/s41524-018-0086-7 ↗
20. 10.1038/s41524-021-00569-710.1038/s41524-021-00569-7 ↗
21. Ronneberger O. · 2015 · 234
22. 10.1109/TPAMI.2021.305996810.1109/TPAMI.2021.3059968 ↗
23. 10.1063/5.010540510.1063/5.0105405 ↗
24. 10.34133/2019/464173910.34133/2019/4641739 ↗
25. 10.1038/s41563-019-0366-810.1038/s41563-019-0366-8 ↗
26. 10.1038/nnano.2015.7510.1038/nnano.2015.75 ↗
27. 10.1038/s41586-018-0298-510.1038/s41586-018-0298-5 ↗
28. 10.3389/fmed.2022.97814610.3389/fmed.2022.978146 ↗
29. 10.1103/RevModPhys.81.10910.1103/RevModPhys.81.109 ↗
30. 10.1038/s41467-021-27646-110.1038/s41467-021-27646-1 ↗
31. 10.1021/acsnano.9b1019610.1021/acsnano.9b10196 ↗
32. 10.1021/acsnano.2c0995210.1021/acsnano.2c09952 ↗
33. 10.1038/nnano.2017.10010.1038/nnano.2017.100 ↗
34. 10.1038/s41563-023-01618-w10.1038/s41563-023-01618-w ↗
35. 10.1021/acs.jpclett.2c0245410.1021/acs.jpclett.2c02454 ↗
36. 10.1103/PhysRevB.103.L12110210.1103/PhysRevB.103.L121102 ↗