journal article·2024-09-26Open access

Random forest prediction of crystal structure from electron diffraction patterns incorporating multiple scattering

Samuel P. Gleason, Alexander Rakowski, Stephanie M. Ribet, Steven E. Zeltmann, Benjamin H. Savitzky, Matthew Henderson, Jim Ciston, Colin Ophus

Physical Review Materials· Volume 8· Issue 9

Abstract

Diffraction is the most common method for solving unknown crystal structures, but nanoscale heterogeneity poses substantial challenges. Here we train random forest models to predict the crystal system, space group, and lattice parameters from one or more unknown 2D electron diffraction patterns. We apply this architecture to a 4D-STEM scan of over 100 gold nanoparticles, accurately predicting the crystal structure and lattice constants. Our ML architecture significantly accelerates the analysis of electron diffraction patterns, particularly in the case of unknown crystal structures at speeds amenable to live analysis. This work also releases ~360 million simulated 2D dynamical electron diffraction patterns from 36,000 materials, each with 100 unique crystal orientations and 100 specimen thicknesses.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: X-ray Diffraction in Crystallography · Machine Learning in Materials Science · Nuclear Physics and Applications

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

Affiliations

Lawrence Berkeley National Laboratory

University of California, Berkeley

Cornell University

Funding

Office of Science · Basic Energy Sciences · U.S. Department of Energy

References (64)

Show source-provided references
1. D. E. Sands · 1993
2. 10.1007/s12039-010-0055-210.1007/s12039-010-0055-2 ↗
3. 10.1073/pnas.210572211810.1073/pnas.2105722118 ↗
4. 10.1038/s41467-019-08490-w10.1038/s41467-019-08490-w ↗
5. 10.1016/j.mtchem.2020.10036310.1016/j.mtchem.2020.100363 ↗
6. 10.3390/e1803010210.3390/e18030102 ↗
7. 10.1016/j.ijrmhm.2018.04.02110.1016/j.ijrmhm.2018.04.021 ↗
8. 10.1103/PhysRevB.42.270710.1103/PhysRevB.42.2707 ↗
9. 10.1103/PhysRevLett.91.13550310.1103/PhysRevLett.91.135503 ↗
10. 10.1021/cm960218d10.1021/cm960218d ↗
11. 10.1107/S205327331500126610.1107/S2053273315001266 ↗
12. 10.1103/PhysRevMaterials.5.10500310.1103/PhysRevMaterials.5.105003 ↗
13. 10.1146/annurev-matsci-080921-09264610.1146/annurev-matsci-080921-092646 ↗
14. 10.1038/nature0554510.1038/nature05545 ↗
15. 10.1038/nature2104210.1038/nature21042 ↗
16. 10.1038/srep0394510.1038/srep03945 ↗
17. 10.1016/j.micron.2017.02.00710.1016/j.micron.2017.02.007 ↗
18. 10.1002/adma.20211039410.1002/adma.202110394 ↗
19. 10.1016/j.cocis.2018.01.01010.1016/j.cocis.2018.01.010 ↗
20. 10.1038/s41592-019-0395-x10.1038/s41592-019-0395-x ↗
21. J. Zuo · 2013
22. 10.1021/acscentsci.9b0039410.1021/acscentsci.9b00394 ↗
23. A. Authier · 200610.1107/97809553602060000104 ↗
24. M. De Graef · 200310.1017/CBO9780511615092 ↗
25. 10.1038/s41570-021-00302-410.1038/s41570-021-00302-4 ↗
26. 10.1017/S143192762200010110.1017/S1431927622000101 ↗
27. 10.1107/S0365110X6700320210.1107/S0365110X67003202 ↗
28. A. S. Eggeman · 2012
29. 10.1016/j.ultramic.2023.11373210.1016/j.ultramic.2023.113732 ↗
30. 10.1038/s41557-023-01186-110.1038/s41557-023-01186-1 ↗
31. 10.1016/j.ultramic.2022.11350310.1016/j.ultramic.2022.113503 ↗
32. 10.1017/S143192762101253810.1017/S1431927621012538 ↗
33. 10.1016/j.ultramic.2006.04.03210.1016/j.ultramic.2006.04.032 ↗
34. 10.1017/S143192762002441110.1017/S1431927620024411 ↗
35. 10.1017/S143192761901038910.1017/S1431927619010389 ↗
36. 10.1017/S143192761900049710.1017/S1431927619000497 ↗
37. S. Zaefferer · 1994
38. E. Rauch · Arch. Metall. Mater. · 2005 · 50 · 87
39. 10.1016/j.ultramic.2016.07.00710.1016/j.ultramic.2016.07.007 ↗
40. 10.1016/j.ultramic.2022.11351710.1016/j.ultramic.2022.113517 ↗
41. 10.1107/S205225252000403010.1107/S2052252520004030 ↗
42. 10.1016/j.sbi.2014.03.00410.1016/j.sbi.2014.03.004 ↗
43. 10.1038/s43586-022-00095-w10.1038/s43586-022-00095-w ↗
44. 10.1186/s40679-019-0063-310.1186/s40679-019-0063-3 ↗
45. 10.1063/5.013054610.1063/5.0130546 ↗
46. 10.1107/S205327332300468010.1107/S2053273323004680 ↗
47. 10.1038/s41524-021-00527-310.1038/s41524-021-00527-3 ↗
48. 10.1038/s41524-022-00960-y10.1038/s41524-022-00960-y ↗
49. 10.1016/j.ultramic.2024.11402110.1016/j.ultramic.2024.114021 ↗
50. 10.1016/j.ultramic.2021.11325610.1016/j.ultramic.2021.113256 ↗
51. 10.1038/s41524-022-00939-910.1038/s41524-022-00939-9 ↗
52. 10.1126/science.aay306210.1126/science.aay3062 ↗
53. 10.1039/D1RA07156D10.1039/D1RA07156D ↗
54. 10.1126/sciadv.aaw194910.1126/sciadv.aaw1949 ↗
55. 10.1073/pnas.230924012010.1073/pnas.2309240120 ↗
56. 10.1038/s41524-024-01408-110.1038/s41524-024-01408-1 ↗
57. 10.1039/D0NA00590H10.1039/D0NA00590H ↗
58. 10.1038/s41467-022-30923-210.1038/s41467-022-30923-2 ↗
59. 10.1063/1.481232310.1063/1.4812323 ↗
60. 10.1017/S143192762100047710.1017/S1431927621000477 ↗
61. F. Pedregosa · J. Mach. Learn. Res. · 2011 · 12 · 2825
62. 10.1111/j.1365-2818.1983.tb04222.x10.1111/j.1365-2818.1983.tb04222.x ↗
63. 10.1038/ncomms1181910.1038/ncomms11819 ↗
64. 10.1016/j.ssc.2009.05.04610.1016/j.ssc.2009.05.046 ↗