journal article·2022-11-17

Machine-learning-based prediction of first-principles XANES spectra for amorphous materials

Haruki Hirai, Takumi Iizawa, Tomoyuki Tamura, Masayuki Karasuyama, Ryo Kobayashi, Takakazu Hirose

Physical Review Materials· Volume 6· Issue 11
Publisher page

Abstract

In this paper, a machine-learning-based method is proposed for predicting the x-ray absorption near-edge structure (XANES) for local configurations specific to amorphous materials. A combination of molecular dynamics and first-principles XANES simulations was adopted. The XANES spectrum was assumed to be accurately represented by linear regression of the local atomic descriptors. A comprehensive prediction of Si $K$-edge XANES spectra was performed based on an atom-centered symmetry function, smooth overlap of atomic positions, local many-body tensor representation, and spectral neighbor analysis potential. Furthermore, prediction accuracy was improved by compression of XANES spectral data and efficient sampling of training data.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: X-ray Spectroscopy and Fluorescence Analysis · Machine Learning in Materials Science · X-ray Diffraction in Crystallography

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

References (51)

Show source-provided references
1. 10.1093/jmicro/dfz10910.1093/jmicro/dfz109 ↗
2. 10.1126/science.276.5317.139510.1126/science.276.5317.1395 ↗
3. 10.1149/1.272474110.1149/1.2724741 ↗
4. 10.1149/1.204399410.1149/1.2043994 ↗
5. 10.1149/1.216042910.1149/1.2160429 ↗
6. 10.1016/S0378-7753(00)00385-210.1016/S0378-7753(00)00385-2 ↗
7. 10.1038/nnano.2007.41110.1038/nnano.2007.411 ↗
8. 10.1016/S0022-3093(03)00031-010.1016/S0022-3093(03)00031-0 ↗
9. 10.1149/1.178717310.1149/1.1787173 ↗
10. 10.1016/j.ssi.2017.03.00810.1016/j.ssi.2017.03.008 ↗
11. 10.1016/j.ssc.2017.10.00410.1016/j.ssc.2017.10.004 ↗
12. 10.1063/1.481232310.1063/1.4812323 ↗
13. 10.1103/PhysRev.136.B86410.1103/PhysRev.136.B864 ↗
14. 10.1103/PhysRev.140.A113310.1103/PhysRev.140.A1133 ↗
15. 10.1103/PhysRevB.50.1795310.1103/PhysRevB.50.17953 ↗
16. 10.1103/PhysRevB.55.200510.1103/PhysRevB.55.2005 ↗
17. 10.1103/PhysRevB.59.175810.1103/PhysRevB.59.1758 ↗
18. 10.1103/PhysRevB.85.20521010.1103/PhysRevB.85.205210 ↗
19. 10.1016/j.commatsci.2021.11055510.1016/j.commatsci.2021.110555 ↗
20. 10.1063/1.355371710.1063/1.3553717 ↗
21. 10.1002/qua.2492710.1002/qua.24927 ↗
22. 10.1039/C6CP00415F10.1039/C6CP00415F ↗
23. 10.1016/j.jcp.2014.12.01810.1016/j.jcp.2014.12.018 ↗
24. 10.1063/1.501764110.1063/1.5017641 ↗
25. 10.1137/15M105418310.1137/15M1054183 ↗
26. 10.21105/joss.0276810.21105/joss.02768 ↗
27. 10.1103/PhysRevB.76.15331010.1103/PhysRevB.76.153310 ↗
28. 10.1103/PhysRevLett.77.386510.1103/PhysRevLett.77.3865 ↗
29. 10.1103/PhysRevB.62.790110.1103/PhysRevB.62.7901 ↗
30. 10.1063/1.137831110.1063/1.1378311 ↗
31. 10.1103/PhysRevB.77.08520710.1103/PhysRevB.77.085207 ↗
32. 10.1038/4456510.1038/44565 ↗
33. 10.1016/j.cpc.2019.10694910.1016/j.cpc.2019.106949 ↗
34. 10.1021/acs.accounts.0c0040310.1021/acs.accounts.0c00403 ↗
35. 10.1016/j.cpc.2021.10817110.1016/j.cpc.2021.108171 ↗
36. 10.1103/PhysRevB.98.09410410.1103/PhysRevB.98.094104 ↗
37. 10.1103/PhysRevMaterials.4.11360210.1103/PhysRevMaterials.4.113602 ↗
38. 10.1021/acs.jpca.9b0872310.1021/acs.jpca.9b08723 ↗
39. 10.1103/PhysRevLett.125.16600110.1103/PhysRevLett.125.166001 ↗
40. 10.1063/5.007048810.1063/5.0070488 ↗
41. 10.1103/PhysRevB.99.01410410.1103/PhysRevB.99.014104 ↗
42. 10.1016/j.jcp.2022.11094610.1016/j.jcp.2022.110946 ↗
43. 10.1103/PhysRevB.102.23513010.1103/PhysRevB.102.235130 ↗
44. 10.1021/acs.chemmater.1c0425210.1021/acs.chemmater.1c04252 ↗
45. 10.1016/j.ultramic.2016.08.00610.1016/j.ultramic.2016.08.006 ↗
46. 10.1103/PhysRevB.54.1116910.1103/PhysRevB.54.11169 ↗
47. 10.1103/PhysRevLett.98.14640110.1103/PhysRevLett.98.146401 ↗
48. 10.1103/PhysRevB.99.06410310.1103/PhysRevB.99.064103 ↗
49. 10.1103/PhysRevB.92.14411110.1103/PhysRevB.92.144111 ↗
50. 10.1103/PhysRevX.8.04104810.1103/PhysRevX.8.041048 ↗
51. 10.1038/s41524-022-00768-w10.1038/s41524-022-00768-w ↗