1
|
Simonnet T, Grangeon S, Claret F, Maubec N, Fall MD, Harba R, Galerne B. Phase quantification using deep neural network processing of XRD patterns. IUCRJ 2024; 11:859-870. [PMID: 39133544 PMCID: PMC11364039 DOI: 10.1107/s2052252524006766] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/23/2023] [Accepted: 07/10/2024] [Indexed: 08/13/2024]
Abstract
Mineral identification and quantification are key to the understanding and, hence, the capacity to predict material properties. The method of choice for mineral quantification is powder X-ray diffraction (XRD), generally using a Rietveld refinement approach. However, a successful Rietveld refinement requires preliminary identification of the phases that make up the sample. This is generally carried out manually, and this task becomes extremely long or virtually impossible in the case of very large datasets such as those from synchrotron X-ray diffraction computed tomography. To circumvent this issue, this article proposes a novel neural network (NN) method for automating phase identification and quantification. An XRD pattern calculation code was used to generate large datasets of synthetic data that are used to train the NN. This approach offers significant advantages, including the ability to construct databases with a substantial number of XRD patterns and the introduction of extensive variability into these patterns. To enhance the performance of the NN, a specifically designed loss function for proportion inference was employed during the training process, offering improved efficiency and stability compared with traditional functions. The NN, trained exclusively with synthetic data, proved its ability to identify and quantify mineral phases on synthetic and real XRD patterns. Trained NN errors were equal to 0.5% for phase quantification on the synthetic test set, and 6% on the experimental data, in a system containing four phases of contrasting crystal structures (calcite, gibbsite, dolomite and hematite). The proposed method is freely available on GitHub and allows for major advances since it can be applied to any dataset, regardless of the mineral phases present.
Collapse
Affiliation(s)
- Titouan Simonnet
- Institut Denis Poisson, Université d’Orléans, Université de Tours, CNRS, France
- BRGM, 45060Orléans, France
- Laboratoire PRISME, Université d’Orléans, INSA Centre Val de Loire, France
| | | | | | | | - Mame Diarra Fall
- Institut Denis Poisson, Université d’Orléans, Université de Tours, CNRS, France
| | - Rachid Harba
- Laboratoire PRISME, Université d’Orléans, INSA Centre Val de Loire, France
| | - Bruno Galerne
- Institut Denis Poisson, Université d’Orléans, Université de Tours, CNRS, France
- Institut Universitaire de France (IUF)France
| |
Collapse
|
2
|
Zhang S, Cao B, Su T, Wu Y, Feng Z, Xiong J, Zhang TY. Crystallographic phase identifier of a convolutional self-attention neural network (CPICANN) on powder diffraction patterns. IUCRJ 2024; 11:634-642. [PMID: 38958016 PMCID: PMC11220882 DOI: 10.1107/s2052252524005323] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Accepted: 06/05/2024] [Indexed: 07/04/2024]
Abstract
Spectroscopic data, particularly diffraction data, are essential for materials characterization due to their comprehensive crystallographic information. The current crystallographic phase identification, however, is very time consuming. To address this challenge, we have developed a real-time crystallographic phase identifier based on a convolutional self-attention neural network (CPICANN). Trained on 692 190 simulated powder X-ray diffraction (XRD) patterns from 23 073 distinct inorganic crystallographic information files, CPICANN demonstrates superior phase-identification power. Single-phase identification on simulated XRD patterns yields 98.5 and 87.5% accuracies with and without elemental information, respectively, outperforming JADE software (68.2 and 38.7%, respectively). Bi-phase identification on simulated XRD patterns achieves 84.2 and 51.5% accuracies, respectively. In experimental settings, CPICANN achieves an 80% identification accuracy, surpassing JADE software (61%). Integration of CPICANN into XRD refinement software will significantly advance the cutting-edge technology in XRD materials characterization.
Collapse
Affiliation(s)
- Shouyang Zhang
- Materials Genome InstituteShanghai UniversityShanghai200444People’s Republic of China
| | - Bin Cao
- Guangzhou Municipal Key Laboratory of Materials Informatics, Sustainable Energy and Environment Thrust, Advanced Materials Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou511400, Guangdong, People’s Republic of China
| | - Tianhao Su
- Materials Genome InstituteShanghai UniversityShanghai200444People’s Republic of China
| | - Yue Wu
- Materials Genome InstituteShanghai UniversityShanghai200444People’s Republic of China
| | - Zhenjie Feng
- Materials Genome InstituteShanghai UniversityShanghai200444People’s Republic of China
| | - Jie Xiong
- Materials Genome InstituteShanghai UniversityShanghai200444People’s Republic of China
| | - Tong-Yi Zhang
- Materials Genome InstituteShanghai UniversityShanghai200444People’s Republic of China
- Guangzhou Municipal Key Laboratory of Materials Informatics, Sustainable Energy and Environment Thrust, Advanced Materials Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou511400, Guangdong, People’s Republic of China
| |
Collapse
|
3
|
Poline V, Purushottam Raj Purohit RRP, Bordet P, Blanc N, Martinetto P. Neural networks for rapid phase quantification of cultural heritage X-ray powder diffraction data. J Appl Crystallogr 2024; 57:831-841. [PMID: 38846765 PMCID: PMC11151672 DOI: 10.1107/s1600576724003704] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2023] [Accepted: 04/23/2024] [Indexed: 06/09/2024] Open
Abstract
Recent developments in synchrotron radiation facilities have increased the amount of data generated during acquisitions considerably, requiring fast and efficient data processing techniques. Here, the application of dense neural networks (DNNs) to data treatment of X-ray diffraction computed tomography (XRD-CT) experiments is presented. Processing involves mapping the phases in a tomographic slice by predicting the phase fraction in each individual pixel. DNNs were trained on sets of calculated XRD patterns generated using a Python algorithm developed in-house. An initial Rietveld refinement of the tomographic slice sum pattern provides additional information (peak widths and integrated intensities for each phase) to improve the generation of simulated patterns and make them closer to real data. A grid search was used to optimize the network architecture and demonstrated that a single fully connected dense layer was sufficient to accurately determine phase proportions. This DNN was used on the XRD-CT acquisition of a mock-up and a historical sample of highly heterogeneous multi-layered decoration of a late medieval statue, called 'applied brocade'. The phase maps predicted by the DNN were in good agreement with other methods, such as non-negative matrix factorization and serial Rietveld refinements performed with TOPAS, and outperformed them in terms of speed and efficiency. The method was evaluated by regenerating experimental patterns from predictions and using the R-weighted profile as the agreement factor. This assessment allowed us to confirm the accuracy of the results.
Collapse
Affiliation(s)
- Victor Poline
- Univ. Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, 38000 Grenoble, France
| | | | - Pierre Bordet
- Univ. Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, 38000 Grenoble, France
| | - Nils Blanc
- Univ. Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, 38000 Grenoble, France
| | - Pauline Martinetto
- Univ. Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, 38000 Grenoble, France
| |
Collapse
|
4
|
Chen L, Wang B, Zhang W, Zheng S, Chen Z, Zhang M, Dong C, Pan F, Li S. Crystal Structure Assignment for Unknown Compounds from X-ray Diffraction Patterns with Deep Learning. J Am Chem Soc 2024; 146:8098-8109. [PMID: 38477574 DOI: 10.1021/jacs.3c11852] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/14/2024]
Abstract
Determining the structures of previously unseen compounds from experimental characterizations is a crucial part of materials science. It requires a step of searching for the structure type that conforms to the lattice of the unknown compound, which enables the pattern matching process for characterization data, such as X-ray diffraction (XRD) patterns. However, this procedure typically places a high demand on domain expertise, thus creating an obstacle for computer-driven automation. Here, we address this challenge by leveraging a deep-learning model composed of a union of convolutional residual neural networks. The accuracy of the model is demonstrated on a dataset of over 60,000 different compounds for 100 structure types, and additional categories can be integrated without the need to retrain the existing networks. We also unravel the operation of the deep-learning black box and highlight the way in which the resemblance between the unknown compound and a structure type is quantified based on both local and global characteristics in XRD patterns. This computational tool opens new avenues for automating structure analysis on materials unearthed in high-throughput experimentation.
Collapse
Affiliation(s)
- Litao Chen
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Bingxu Wang
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Wentao Zhang
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Shisheng Zheng
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Zhefeng Chen
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Mingzheng Zhang
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Cheng Dong
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Feng Pan
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| | - Shunning Li
- School of Advanced Materials, Peking University, Shenzhen Graduate School, Shenzhen 518055, People's Republic of China
| |
Collapse
|
5
|
Sun M, Dong Z, Wu L, Yao H, Niu W, Xu D, Chen P, Gupta HS, Zhang Y, Dong Y, Chen C, Zhao L. Fast extraction of three-dimensional nanofiber orientation from WAXD patterns using machine learning. IUCRJ 2023; 10:297-308. [PMID: 36961758 PMCID: PMC10161767 DOI: 10.1107/s205225252300204x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Accepted: 03/03/2023] [Indexed: 05/06/2023]
Abstract
Structural disclosure of biological materials can help our understanding of design disciplines in nature and inspire research for artificial materials. Synchrotron microfocus X-ray diffraction is one of the main techniques for characterizing hierarchically structured biological materials, especially the 3D orientation distribution of their interpenetrating nanofiber networks. However, extraction of 3D fiber orientation from X-ray patterns is still carried out by iterative parametric fitting, with disadvantages of time consumption and demand for expertise and initial parameter estimates. When faced with high-throughput experiments, existing analysis methods cannot meet the real time analysis challenges. In this work, using the assumption that the X-ray illuminated volume is dominated by two groups of nanofibers in a gradient biological composite, a machine-learning based method is proposed for fast and automatic fiber orientation metrics prediction from synchrotron X-ray micro-focused diffraction data. The simulated data were corrupted in the training procedure to guarantee the prediction ability of the trained machine-learning algorithm in real-world experimental data predictions. Label transformation was used to resolve the jump discontinuity problem when predicting angle parameters. The proposed method shows promise for application in the automatic data-processing pipeline for fast analysis of the vast data generated from multiscale diffraction-based tomography characterization of textured biomaterials.
Collapse
Affiliation(s)
- Minghui Sun
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Zheng Dong
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Liyuan Wu
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Haodong Yao
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Wenchao Niu
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Deting Xu
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Ping Chen
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Himadri S Gupta
- School of Engineering and Material Science, Queen Mary University of London, London E1 4NS, United Kingdom
| | - Yi Zhang
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Yuhui Dong
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Chunying Chen
- University of Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| | - Lina Zhao
- Multidisciplinary Initiative Center, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, People's Republic of China
| |
Collapse
|
6
|
Utimula K, Yano M, Kimoto H, Hongo K, Nakano K, Maezono R. Feature Space of XRD Patterns Constructed by an Autoencoder. ADVANCED THEORY AND SIMULATIONS 2022. [DOI: 10.1002/adts.202200613] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Affiliation(s)
- Keishu Utimula
- School of Materials Science JAIST Asahidai 1‐1 Nomi Ishikawa 923‐1292 Japan
| | - Masao Yano
- Toyota Motor Corporation 1, Toyota‐cho Toyota Aichi 471‐8572 Japan
| | - Hiroyuki Kimoto
- Toyota Motor Corporation 1, Toyota‐cho Toyota Aichi 471‐8572 Japan
| | - Kenta Hongo
- Research Center for Advanced Computing Infrastructure JAIST Asahidai 1‐1 Nomi Ishikawa 923‐1292 Japan
| | - Kousuke Nakano
- School of Information Science JAIST Asahidai 1‐1 Nomi Ishikawa 923‐1292 Japan
| | - Ryo Maezono
- School of Information Science JAIST Asahidai 1‐1 Nomi Ishikawa 923‐1292 Japan
| |
Collapse
|
7
|
Wang Y, Goh B, Moorehead M, Hattrick-Simpers J, Couet A. High-Throughput Electrochemistry to Study Materials Degradation in Extreme Environments. Anal Chem 2022; 94:16528-16537. [DOI: 10.1021/acs.analchem.2c03325] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Affiliation(s)
- Yafei Wang
- Department of Engineering Physics, University of Wisconsin−Madison, Madison, Wisconsin53715, United States
- School of Nuclear Science and Engineering, Shanghai Jiao Tong University, Shanghai200240, China
| | - Bonita Goh
- Department of Engineering Physics, University of Wisconsin−Madison, Madison, Wisconsin53715, United States
| | - Michael Moorehead
- Department of Engineering Physics, University of Wisconsin−Madison, Madison, Wisconsin53715, United States
| | - Jason Hattrick-Simpers
- Department of Materials Science & Engineering, University of Toronto, Toronto, OntarioM5S 3E4, Canada
| | - Adrien Couet
- Department of Engineering Physics, University of Wisconsin−Madison, Madison, Wisconsin53715, United States
| |
Collapse
|
8
|
Hong D, Oh J, Bang K, Kwon S, Yun SY, Lee HM. Interpretable Deep Learning Model for Analyzing the Relationship between the Electronic Structure and Chemisorption Property. J Phys Chem Lett 2022; 13:8628-8634. [PMID: 36082963 DOI: 10.1021/acs.jpclett.2c02293] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
The use of machine learning (ML) is exploding in materials science as a result of its high predictive performance of material properties. Tremendous trainable parameters are required to build an outperforming predictive model, which makes it impossible to retrace how the model predicts well. However, it is necessary to develop a ML model that can extract human-understandable knowledge while maintaining performance for a universal application to materials science. In this study, we developed a deep learning model that can interpret the correlation between surface electronic density of states (DOSs) of materials and their chemisorption property using the attention mechanism that provides which part of DOS is important to predict adsorption energies. The developed model constructs the well-known d-band center theory without any prior knowledge. This work shows that human-interpretable knowledge can be extracted from complex ML models.
Collapse
Affiliation(s)
- Doosun Hong
- Department of Materials Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
| | - Jaehoon Oh
- Graduate School of Data Science, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
| | - Kihoon Bang
- Department of Materials Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
| | - Soonho Kwon
- Materials and Process Simulation Center (MSC), California Institute of Technology, Pasadena, California 91125, United States
| | - Se-Young Yun
- Kim Jaechul Graduate School of Artificial Intelligence, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
| | - Hyuck Mo Lee
- Department of Materials Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
| |
Collapse
|
9
|
Baptista de Castro P, Terashima K, Esparza Echevarria MG, Takeya H, Takano Y. XERUS: An Open‐Source Tool for Quick XRD Phase Identification and Refinement Automation. ADVANCED THEORY AND SIMULATIONS 2022. [DOI: 10.1002/adts.202100588] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/30/2022]
Affiliation(s)
- Pedro Baptista de Castro
- National Institute for Materials Science 1‐2‐1 Sengen Tsukuba Ibaraki 305‐0047 Japan
- University of Tsukuba 1‐1‐1 Tennodai Tsukuba Ibaraki 305‐8577 Japan
| | - Kensei Terashima
- National Institute for Materials Science 1‐2‐1 Sengen Tsukuba Ibaraki 305‐0047 Japan
| | - Miren Garbine Esparza Echevarria
- National Institute for Materials Science 1‐2‐1 Sengen Tsukuba Ibaraki 305‐0047 Japan
- University of Tsukuba 1‐1‐1 Tennodai Tsukuba Ibaraki 305‐8577 Japan
| | - Hiroyuki Takeya
- National Institute for Materials Science 1‐2‐1 Sengen Tsukuba Ibaraki 305‐0047 Japan
| | - Yoshihiko Takano
- National Institute for Materials Science 1‐2‐1 Sengen Tsukuba Ibaraki 305‐0047 Japan
- University of Tsukuba 1‐1‐1 Tennodai Tsukuba Ibaraki 305‐8577 Japan
| |
Collapse
|