Presentation | 2023-06-29 Crystal structure X-ray absorption spectrum prediction and valence ratio estimation based on Gaussian process regression Takumi Iwashita, Haruki Hirai, Ryo Kobayashi, Tomoyuki Tamura, Masayuki Karasuyama, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | X-ray absorption spectra are known as a useful experimental measurement technique for crystal structure analysis. Spectral data can provide clues to the structure of a crystal because they reflect the structural information of the arrangement of atoms in the crystal. However, since the experimentally obtained spectrum is an averaged spectrum of the crystal structure, it is not possible to separate multiple different local structures in a single crystal. Recently, simulation calculations of spectra based on theoretical calculations have become available, and structural analysis can be performed using spectra calculated from structural models, but the computational cost is very high and is not comprehensive. In this study, we propose a method based on Gaussian process regression for prediction spectrum and valence ratio estimation of crystal structure using SiO data as an example, which is a battery material. It is inferred that this ratio affects the shape of the spectrum, but this ratio cannot be directly obtained from the experimental spectrum. Therefore, we first consider the prediction spectrum for each valence ratio, using the simulation data as training data. Since each valence ratio retains structural fluctuations, we consider these fluctuations as input uncertainties and describe the construction of a prediction distribution using Gaussian process regression. Based on the estimated prediction distribution for each valence, we propose a method for inferentially inferring the valence ratio from the average spectrum of the entire crystal measured experimentally. The effectiveness of the method is verified by computer experiments. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Gaussian Process Regression / Multitask Gaussian Process Regression / Input Uncertain Gaussian Process Regression |
Paper # | NC2023-3,IBISML2023-3 |
Date of Issue | 2023-06-22 (NC, IBISML) |
Conference Information | |
Committee | NC / IBISML / IPSJ-BIO / IPSJ-MPS |
---|---|
Conference Date | 2023/6/29(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | OIST Conference Center |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hirokazu Tanaka(Tokyo City Univ.) / Masashi Sugiyama(Univ. of Tokyo) |
Vice Chair | Jun Izawa(Univ. of Tsukub) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Jun Izawa(NTT) / Toshihiro Kamishima(NAIST) / Koji Tsuda(NTT) / (Hokkaido Univ.) |
Assistant | Yoshimasa Tawatsuji(Waseda Univ.) / Takato Horii(Osaka Univ.) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Bioinformatics and Genomics / Special Interest Group on Mathematical Modeling and Problem Solving |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Crystal structure X-ray absorption spectrum prediction and valence ratio estimation based on Gaussian process regression |
Sub Title (in English) | |
Keyword(1) | Gaussian Process Regression |
Keyword(2) | Multitask Gaussian Process Regression |
Keyword(3) | Input Uncertain Gaussian Process Regression |
1st Author's Name | Takumi Iwashita |
1st Author's Affiliation | Nagoya Institute of Technology(NIT) |
2nd Author's Name | Haruki Hirai |
2nd Author's Affiliation | Nagoya Institute of Technology(NIT) |
3rd Author's Name | Ryo Kobayashi |
3rd Author's Affiliation | Nagoya Institute of Technology(NIT) |
4th Author's Name | Tomoyuki Tamura |
4th Author's Affiliation | Nagoya Institute of Technology(NIT) |
5th Author's Name | Masayuki Karasuyama |
5th Author's Affiliation | Nagoya Institute of Technology(NIT) |
Date | 2023-06-29 |
Paper # | NC2023-3,IBISML2023-3 |
Volume (vol) | vol.123 |
Number (no) | NC-90,IBISML-91 |
Page | pp.pp.17-24(NC), pp.17-24(IBISML), |
#Pages | 8 |
Date of Issue | 2023-06-22 (NC, IBISML) |