Crystal symmetry classification from powder X-ray diffraction patterns using a convolutional neural network

Zaloga, A. N.; Stanovov, Vladimir; Bezrukova, Oksana E.; Dubinin, P. S.; Yakimov, Igor S.

doi:10.1016/j.mtcomm.2020.101662

Cited by 18 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Zaloga et al 171 also used the ICSD database for XRD pattern generation and CNN models to classify crystals. The models achieved 90.02% and 79.82% accuracy for crystal systems and space groups, respectively.…”

Section: Applicationsmentioning

confidence: 99%

Recent advances and applications of deep learning methods in materials science

et al. 2022

View full text Add to dashboard Cite

Deep learning (DL) is one of the fastest-growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. The recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science.

show abstract

Section: Applicationsmentioning

confidence: 99%

Recent advances and applications of deep learning methods in materials science

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Furthermore, the decoder or a generative model can be used to learn the probability distribution of potential candidate structures as a direct pathway to "invert" the spectra to the structure. 88 Neural network (NN)-based classification for X-ray diffraction (XRD) and other (than XAFS) spectroscopy techniques has been implemented to identify the crystal structure, 90 space groups, 91 etc. An embedding-based approach has also been used to decompose the observed signals into underlying species and their distribution by applying additional constraints and reasoning on the embeddings, as recently shown by crystal structure phase mapping of mixed species using XRD patterns.…”

Section: Machine Learning Approachesmentioning

confidence: 99%

Speciation of Nanocatalysts Using X-ray Absorption Spectroscopy Assisted by Machine Learning

2023

View full text Add to dashboard Cite

The structure and morphology of supported nanoparticle catalysts play important roles in many industrial reactions. Recent progress has identified key aspects of structure−activity relationships at the nanoscale and novel methods to study the local environment of the active sites. X-ray absorption fine structure (XAFS) spectroscopy, despite being a leading technique for this purpose, is hampered significantly by its ensemble-averaging nature which often leads to a bias toward a single "representative" structure. Learning heterogeneous distributions of nanostructures at the inter-and intraparticle levels from the average XAFS spectrum is a formidable challenge that can be overcome in some cases described in this Perspective. We also discuss emerging machine learning techniques for extracting the information about the heterogeneity of metal species from XAFS data.

show abstract

“…Similarly, Zaloga et al [201] also used the ICSD database for XRD pattern generation and CNN models to classify crystals. The models achieved 90.02 % and 79.82 % accuracy for crystal systems and space groups, respectively.…”

Section: Applicationsmentioning

confidence: 99%

Recent Advances and Applications of Deep Learning Methods in Materials Science

Choudhary,

DeCost,

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Crystal symmetry classification from powder X-ray diffraction patterns using a convolutional neural network

Cited by 18 publications

References 13 publications

Recent advances and applications of deep learning methods in materials science

Recent advances and applications of deep learning methods in materials science

Speciation of Nanocatalysts Using X-ray Absorption Spectroscopy Assisted by Machine Learning

Recent Advances and Applications of Deep Learning Methods in Materials Science

Contact Info

Product

Resources

About