Deep-Learning Aided Atomic-Scale Phase Segmentation toward Diagnosing Complex Oxide Cathodes for Lithium-Ion Batteries
Source abstract
Abstract
Phase transformation─a universal phenomenon in materials─plays a key role in determining their properties. Resolving complex phase domains in materials is critical to fostering a new fundamental understanding that facilitates new material development. So far, although conventional classification strategies such as order-parameter methods have been developed to distinguish remarkably disparate phases, highly accurate and efficient phase segmentation for material systems composed of multiphases remains unavailable. Here, by coupling hard-attention-enhanced U-Net network and geometry simulation with atomic-resolution transmission electron microscopy, we successfully developed a deep-learning tool enabling automated atom-by-atom phase segmentation of intertwined phase domains in technologically important cathode materials for lithium-ion batteries. The new strategy outperforms traditional methods and quantitatively elucidates the correlation between the multiple phases formed during battery operation. Our work demonstrates how deep learning can be employed to foster an in-depth understanding of phase transformation-related key issues in complex materials.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Electron and X-Ray Spectroscopy Techniques · Advanced Electron Microscopy Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Physics and Astronomy, University of California Irvine, Irvine, California 92697, United States
Computer Network Information Centre, Chinese Academy of Sciences, Beijing, 100190, P. R. China
University of Chinese Academy of Sciences, Beijing, 100049, P. R. China
BASF Corporation, Iselin, New Jersey 08830, United States
BASF Corporation, Beachwood, Ohio 44122, United States
Funding
BASF Corporation
References (50)
Show source-provided references
1. 10.1126/science.abm261210.1126/science.abm2612 ↗
2. 10.1126/science.aax651110.1126/science.aax6511 ↗
3. 10.1016/j.matt.2020.09.00310.1016/j.matt.2020.09.003 ↗
4. 10.1103/PhysRevLett.120.18610210.1103/PhysRevLett.120.186102 ↗
5. 10.1038/ncomms114910.1038/ncomms1149 ↗
6. 10.1038/ncomms443310.1038/ncomms4433 ↗
7. 10.1103/PhysRevLett.106.16550510.1103/PhysRevLett.106.165505 ↗
8. 10.1021/acsnano.0c0669710.1021/acsnano.0c06697 ↗
9. 10.1021/acs.nanolett.9b0149410.1021/acs.nanolett.9b01494 ↗
10. 10.1038/s41586-022-05115-z10.1038/s41586-022-05115-z ↗
11. 10.1016/j.matt.2021.03.01210.1016/j.matt.2021.03.012 ↗
12. 10.1038/s41563-022-01461-510.1038/s41563-022-01461-5 ↗
13. 10.1038/s41560-023-01267-y10.1038/s41560-023-01267-y ↗
14. 10.1016/j.matt.2023.02.00110.1016/j.matt.2023.02.001 ↗
15. 10.1021/acs.jpcc.2c0592910.1021/acs.jpcc.2c05929 ↗
16. 10.1038/s41467-020-16869-310.1038/s41467-020-16869-3 ↗
17. 10.1038/s41524-019-0152-910.1038/s41524-019-0152-9 ↗
18. 10.1038/s41524-020-00363-x10.1038/s41524-020-00363-x ↗
19. 10.1016/j.aei.2019.10100910.1016/j.aei.2019.101009 ↗
20. 10.1109/TIE.2020.302628510.1109/TIE.2020.3026285 ↗
21. 10.1109/TASLP.2015.250925710.1109/TASLP.2015.2509257 ↗
22. Schwenk H. · Proceedings of COLING 2012: Posters · 2012 · 1071
23. 10.1103/PhysRevLett.120.14530110.1103/PhysRevLett.120.145301 ↗
24. 10.1103/PhysRevMaterials.4.06380110.1103/PhysRevMaterials.4.063801 ↗
25. 10.1038/s41524-022-00952-y10.1038/s41524-022-00952-y ↗
26. 10.1109/TMI.2016.252812910.1109/TMI.2016.2528129 ↗
27. 10.1109/TMI.2016.252580310.1109/TMI.2016.2525803 ↗
28. 10.1109/TVT.2019.289317310.1109/TVT.2019.2893173 ↗
29. Yuan, Y.; Xiong, Z.; Wang, Q. Acm: Adaptive cross-modal graph convolutional neural networks for rgb-d scene recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, 2019; Vol. 33, pp 9176–9184.10.1609/aaai.v33i01.33019176 ↗
30. 10.1557/s43577-022-00413-310.1557/s43577-022-00413-3 ↗
31. 10.1038/s41563-020-00833-z10.1038/s41563-020-00833-z ↗
32. 10.1017/S143192762101039410.1017/S1431927621010394 ↗
33. 10.1017/S143192762201142410.1017/S1431927622011424 ↗
34. 10.1017/S143192762201206510.1017/S1431927622012065 ↗
35. 10.1017/S143192762101267810.1017/S1431927621012678 ↗
36. 10.1021/acsnano.7b0750410.1021/acsnano.7b07504 ↗
37. 10.1021/jacs.1c1246610.1021/jacs.1c12466 ↗
38. 10.1038/s41598-021-84499-w10.1038/s41598-021-84499-w ↗
39. 10.1021/acs.nanolett.1c0086210.1021/acs.nanolett.1c00862 ↗
40. 10.1021/acs.nanolett.1c0385210.1021/acs.nanolett.1c03852 ↗
41. 10.1021/acs.nanolett.2c0110310.1021/acs.nanolett.2c01103 ↗
42. 10.1017/S143192762100016710.1017/S1431927621000167 ↗
43. 10.1017/S143192762100038610.1017/S1431927621000386 ↗
44. 10.1038/s41524-021-00652-z10.1038/s41524-021-00652-z ↗
45. 10.1039/D0TA07706B10.1039/D0TA07706B ↗
46. 10.1021/acsenergylett.3c0016910.1021/acsenergylett.3c00169 ↗
47. Ronneberger O. · 2015 · 234
48. Serra, J.; Suris, D.; Miron, M.; Karatzoglou, A. Overcoming catastrophic forgetting with hard attention to the task. In International Conference on Machine Learning, 2018; PMLR: pp 4548–4557.
49. 10.1103/PhysRevLett.41.12110.1103/PhysRevLett.41.121 ↗
50. 10.1038/ncomms452910.1038/ncomms4529 ↗