journal article·2024-08-21

Single-Image-Based Deep Learning for Precise Atomic Defect Identification

Kangshu Li, Xiaocang Han, Yuan Meng, Junxian Li, Yanhui Hong, Xiang Chen, Jing-Yang You, Lin Yao, Wenchao Hu, Zhiyi Xia, Guolin Ke, Linfeng Zhang, Jin Zhang, Xiaoxu Zhao

Nano Letters· Volume 24· Issue 33
Publisher page

Abstract

Defect engineering is widely used to impart the desired functionalities on materials. Despite the widespread application of atomic-resolution scanning transmission electron microscopy (STEM), traditional methods for defect analysis are highly sensitive to random noise and human bias. While deep learning (DL) presents a viable alternative, it requires extensive amounts of training data with labeled ground truth. Herein, employing cycle generative adversarial networks (CycleGAN) and U-Nets, we propose a method based on a single experimental STEM image to tackle high annotation costs and image noise for defect detection. Not only atomic defects but also oxygen dopants in monolayer MoS 2 are visualized. The method can be readily extended to other two-dimensional systems, as the training is based on unit-cell-level images. Therefore, our results outline novel ways to train the model with minimal data sets, offering great opportunities to fully exploit the power of DL in the materials science community.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Electron Microscopy Techniques and Applications · Electron and X-Ray Spectroscopy Techniques · Integrated Circuits and Semiconductor Failure Analysis

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

Affiliations

School of Materials Science and Engineering, Peking University, Beijing 100871, China

DP Technology, Beijing 100080, China

Department of Physics, National University of Singapore, Singapore 117551

AI for Science Institute, Beijing 100084, China

Funding

Beijing National Laboratory for Molecular Sciences · Ministry of Science and Technology of the People's Republic of China · Songshan Lake Materials Laboratory · Science, Technology and Innovation Commission of Shenzhen Municipality · Beijing Municipal Natural Science Foundation · National Natural Science Foundation of China · Chinese Academy of Sciences

References (43)

Show source-provided references
1. 10.1088/0034-4885/68/10/R0210.1088/0034-4885/68/10/R02 ↗
2. 10.1126/science.274.5294.185310.1126/science.274.5294.1853 ↗
3. 10.1038/s41699-022-00286-910.1038/s41699-022-00286-9 ↗
4. 10.1002/pssr.20200024810.1002/pssr.202000248 ↗
5. 10.1038/ncomms1588110.1038/ncomms15881 ↗
6. 10.1021/acsnano.3c0210310.1021/acsnano.3c02103 ↗
7. 10.1021/jacs.6b0371410.1021/jacs.6b03714 ↗
8. 10.1016/j.ultramic.2016.05.00410.1016/j.ultramic.2016.05.004 ↗
9. 10.1021/acs.nanolett.6b0033410.1021/acs.nanolett.6b00334 ↗
10. 10.1021/acs.nanolett.1c0096610.1021/acs.nanolett.1c00966 ↗
11. 10.1038/ncomms505510.1038/ncomms5055 ↗
12. 10.1038/nature0887910.1038/nature08879 ↗
13. 10.1021/acsnano.7b0902910.1021/acsnano.7b09029 ↗
14. 10.1038/nmat367310.1038/nmat3673 ↗
15. 10.1002/adma.20190023710.1002/adma.201900237 ↗
16. 10.1016/0304-3991(89)90173-310.1016/0304-3991(89)90173-3 ↗
17. 10.1038/s43586-022-00095-w10.1038/s43586-022-00095-w ↗
18. 10.1021/acs.nanolett.6b0504510.1021/acs.nanolett.6b05045 ↗
19. 10.1038/s41746-021-00438-z10.1038/s41746-021-00438-z ↗
20. 10.1038/s41598-018-19379-x10.1038/s41598-018-19379-x ↗
21. 10.1186/s40679-017-0042-510.1186/s40679-017-0042-5 ↗
22. 10.1007/s12194-017-0406-510.1007/s12194-017-0406-5 ↗
23. 10.1016/j.vehcom.2019.10018410.1016/j.vehcom.2019.100184 ↗
24. 10.1038/383812a010.1038/383812a0 ↗
25. 10.1038/s41586-019-0912-110.1038/s41586-019-0912-1 ↗
26. 10.1038/s41524-022-00734-610.1038/s41524-022-00734-6 ↗
27. 10.1021/acsnano.4c0289810.1021/acsnano.4c02898 ↗
28. 10.1038/s42256-022-00555-810.1038/s42256-022-00555-8 ↗
29. 10.1038/s44160-024-00501-z10.1038/s44160-024-00501-z ↗
30. 10.1038/s41524-023-01142-010.1038/s41524-023-01142-0 ↗
31. 10.1021/acsnano.7b0750410.1021/acsnano.7b07504 ↗
32. 10.1021/acs.nanolett.0c0513510.1021/acs.nanolett.0c05135 ↗
33. 10.1021/acs.nanolett.0c0026910.1021/acs.nanolett.0c00269 ↗
34. 10.1038/s41524-021-00642-110.1038/s41524-021-00642-1 ↗
35. 10.1002/advs.20210109910.1002/advs.202101099 ↗
36. 10.1126/sciadv.abd741610.1126/sciadv.abd7416 ↗
37. 10.1038/s41524-019-0152-910.1038/s41524-019-0152-9 ↗
38. 10.1038/s41524-023-01042-310.1038/s41524-023-01042-3 ↗
39. 10.1002/advs.20230250810.1002/advs.202302508 ↗
40. 10.1214/aoms/117772969410.1214/aoms/1177729694 ↗
41. 10.1021/nn500532f10.1021/nn500532f ↗
42. 10.1007/s12274-020-3038-810.1007/s12274-020-3038-8 ↗
43. 10.1038/s41557-018-0136-210.1038/s41557-018-0136-2 ↗