Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction data
To advance the development of materials through data-driven scientific methods, appropriate methods for building machine learning (ML)-ready feature tables from measured and computed data must be established. In materials development, X-ray diffraction (XRD) is an effective technique for analysing c...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Science and Technology of Advanced Materials: Methods |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/27660400.2024.2384352 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846129026368798720 |
|---|---|
| author | Ryo Murakami Taisuke T. Sasaki Hideki Yoshikawa Yoshitaka Matsushita Keitaro Sodeyama Tadakatsu Ohkubo Hiroshi Shinotsuka Kenji Nagata |
| author_facet | Ryo Murakami Taisuke T. Sasaki Hideki Yoshikawa Yoshitaka Matsushita Keitaro Sodeyama Tadakatsu Ohkubo Hiroshi Shinotsuka Kenji Nagata |
| author_sort | Ryo Murakami |
| collection | DOAJ |
| description | To advance the development of materials through data-driven scientific methods, appropriate methods for building machine learning (ML)-ready feature tables from measured and computed data must be established. In materials development, X-ray diffraction (XRD) is an effective technique for analysing crystal structures and other microstructural features that have information that can explain material properties. Therefore, the fully automated extraction of peak features from XRD data without the bias of an analyst is a significant challenge. This study aimed to establish an efficient and robust approach for constructing peak feature tables that follow ML standards (ML-ready) from XRD data. We challenge peak feature extraction in the situation where only the peak function profile is known a priori, without knowledge of the measurement material or crystal structure factor. We utilized Bayesian estimation to extract peak features from XRD data and subsequently performed Bayesian regression analysis with feature selection to predict the material property. The proposed method focused only on the tops of peaks within localized regions of interest (ROIs) and extracted peak features quickly and accurately. This process facilitated the rapid extracting of major peak features from the XRD data and the construction of an ML-ready feature table. We then applied Bayesian linear regression to the maximum energy product [Formula: see text], using the extracted peak features as the explanatory variable. The outcomes yielded reasonable and robust regression results. Thus, the findings of this study indicated that 004 peak height and area were important features for predicting [Formula: see text]. |
| format | Article |
| id | doaj-art-576ae5c6c20e4d168b1c6b8cd991f06c |
| institution | Kabale University |
| issn | 2766-0400 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Science and Technology of Advanced Materials: Methods |
| spelling | doaj-art-576ae5c6c20e4d168b1c6b8cd991f06c2024-12-10T09:58:05ZengTaylor & Francis GroupScience and Technology of Advanced Materials: Methods2766-04002024-12-014110.1080/27660400.2024.2384352Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction dataRyo Murakami0Taisuke T. Sasaki1Hideki Yoshikawa2Yoshitaka Matsushita3Keitaro Sodeyama4Tadakatsu Ohkubo5Hiroshi Shinotsuka6Kenji Nagata7Research Network and Facility Services Division, National Institute for Materials Science, Tsukuba, JapanResearch Center for Magnetic and Spintronic Materials, National Institute for Materials Science, Tsukuba, JapanResearch Network and Facility Services Division, National Institute for Materials Science, Tsukuba, JapanResearch Network and Facility Services Division, National Institute for Materials Science, Tsukuba, JapanCenter for Basic Research on Materials, National Institute for Materials Science, Tsukuba, JapanResearch Center for Magnetic and Spintronic Materials, National Institute for Materials Science, Tsukuba, JapanResearch Network and Facility Services Division, National Institute for Materials Science, Tsukuba, JapanCenter for Basic Research on Materials, National Institute for Materials Science, Tsukuba, JapanTo advance the development of materials through data-driven scientific methods, appropriate methods for building machine learning (ML)-ready feature tables from measured and computed data must be established. In materials development, X-ray diffraction (XRD) is an effective technique for analysing crystal structures and other microstructural features that have information that can explain material properties. Therefore, the fully automated extraction of peak features from XRD data without the bias of an analyst is a significant challenge. This study aimed to establish an efficient and robust approach for constructing peak feature tables that follow ML standards (ML-ready) from XRD data. We challenge peak feature extraction in the situation where only the peak function profile is known a priori, without knowledge of the measurement material or crystal structure factor. We utilized Bayesian estimation to extract peak features from XRD data and subsequently performed Bayesian regression analysis with feature selection to predict the material property. The proposed method focused only on the tops of peaks within localized regions of interest (ROIs) and extracted peak features quickly and accurately. This process facilitated the rapid extracting of major peak features from the XRD data and the construction of an ML-ready feature table. We then applied Bayesian linear regression to the maximum energy product [Formula: see text], using the extracted peak features as the explanatory variable. The outcomes yielded reasonable and robust regression results. Thus, the findings of this study indicated that 004 peak height and area were important features for predicting [Formula: see text].https://www.tandfonline.com/doi/10.1080/27660400.2024.2384352Materials informaticsspectral decompositionBayesian estimationfeature selectionaI-ready |
| spellingShingle | Ryo Murakami Taisuke T. Sasaki Hideki Yoshikawa Yoshitaka Matsushita Keitaro Sodeyama Tadakatsu Ohkubo Hiroshi Shinotsuka Kenji Nagata Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction data Science and Technology of Advanced Materials: Methods Materials informatics spectral decomposition Bayesian estimation feature selection aI-ready |
| title | Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction data |
| title_full | Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction data |
| title_fullStr | Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction data |
| title_full_unstemmed | Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction data |
| title_short | Bayesian inference for peak feature extraction and prediction of material property in X-ray diffraction data |
| title_sort | bayesian inference for peak feature extraction and prediction of material property in x ray diffraction data |
| topic | Materials informatics spectral decomposition Bayesian estimation feature selection aI-ready |
| url | https://www.tandfonline.com/doi/10.1080/27660400.2024.2384352 |
| work_keys_str_mv | AT ryomurakami bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata AT taisuketsasaki bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata AT hidekiyoshikawa bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata AT yoshitakamatsushita bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata AT keitarosodeyama bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata AT tadakatsuohkubo bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata AT hiroshishinotsuka bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata AT kenjinagata bayesianinferenceforpeakfeatureextractionandpredictionofmaterialpropertyinxraydiffractiondata |