A deep convolutional neural network for real-time full profile analysis of big powder diffraction data

Abstract We present Parameter Quantification Network (PQ-Net), a regression deep convolutional neural network providing quantitative analysis of powder X-ray diffraction patterns from multi-phase systems. The network is tested against simulated and experimental datasets of increasing complexity with...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hongyang Dong, Keith T. Butler, Dorota Matras, Stephen W. T. Price, Yaroslav Odarchenko, Rahul Khatry, Andrew Thompson, Vesna Middelkoop, Simon D. M. Jacques, Andrew M. Beale, Antonis Vamvakeros
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Acceso en línea:https://doaj.org/article/7adac6f0b28a45c1aa8cd163d3fb007b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7adac6f0b28a45c1aa8cd163d3fb007b
record_format dspace
spelling oai:doaj.org-article:7adac6f0b28a45c1aa8cd163d3fb007b2021-12-02T15:45:30ZA deep convolutional neural network for real-time full profile analysis of big powder diffraction data10.1038/s41524-021-00542-42057-3960https://doaj.org/article/7adac6f0b28a45c1aa8cd163d3fb007b2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00542-4https://doaj.org/toc/2057-3960Abstract We present Parameter Quantification Network (PQ-Net), a regression deep convolutional neural network providing quantitative analysis of powder X-ray diffraction patterns from multi-phase systems. The network is tested against simulated and experimental datasets of increasing complexity with the last one being an X-ray diffraction computed tomography dataset of a multi-phase Ni-Pd/CeO2-ZrO2/Al2O3 catalytic material system consisting of ca. 20,000 diffraction patterns. It is shown that the network predicts accurate scale factor, lattice parameter and crystallite size maps for all phases, which are comparable to those obtained through full profile analysis using the Rietveld method, also providing a reliable uncertainty measure on the results. The main advantage of PQ-Net is its ability to yield these results orders of magnitude faster showing its potential as a tool for real-time diffraction data analysis during in situ/operando experiments.Hongyang DongKeith T. ButlerDorota MatrasStephen W. T. PriceYaroslav OdarchenkoRahul KhatryAndrew ThompsonVesna MiddelkoopSimon D. M. JacquesAndrew M. BealeAntonis VamvakerosNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-9 (2021)
institution DOAJ
collection DOAJ
language EN
topic Materials of engineering and construction. Mechanics of materials
TA401-492
Computer software
QA76.75-76.765
spellingShingle Materials of engineering and construction. Mechanics of materials
TA401-492
Computer software
QA76.75-76.765
Hongyang Dong
Keith T. Butler
Dorota Matras
Stephen W. T. Price
Yaroslav Odarchenko
Rahul Khatry
Andrew Thompson
Vesna Middelkoop
Simon D. M. Jacques
Andrew M. Beale
Antonis Vamvakeros
A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
description Abstract We present Parameter Quantification Network (PQ-Net), a regression deep convolutional neural network providing quantitative analysis of powder X-ray diffraction patterns from multi-phase systems. The network is tested against simulated and experimental datasets of increasing complexity with the last one being an X-ray diffraction computed tomography dataset of a multi-phase Ni-Pd/CeO2-ZrO2/Al2O3 catalytic material system consisting of ca. 20,000 diffraction patterns. It is shown that the network predicts accurate scale factor, lattice parameter and crystallite size maps for all phases, which are comparable to those obtained through full profile analysis using the Rietveld method, also providing a reliable uncertainty measure on the results. The main advantage of PQ-Net is its ability to yield these results orders of magnitude faster showing its potential as a tool for real-time diffraction data analysis during in situ/operando experiments.
format article
author Hongyang Dong
Keith T. Butler
Dorota Matras
Stephen W. T. Price
Yaroslav Odarchenko
Rahul Khatry
Andrew Thompson
Vesna Middelkoop
Simon D. M. Jacques
Andrew M. Beale
Antonis Vamvakeros
author_facet Hongyang Dong
Keith T. Butler
Dorota Matras
Stephen W. T. Price
Yaroslav Odarchenko
Rahul Khatry
Andrew Thompson
Vesna Middelkoop
Simon D. M. Jacques
Andrew M. Beale
Antonis Vamvakeros
author_sort Hongyang Dong
title A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
title_short A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
title_full A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
title_fullStr A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
title_full_unstemmed A deep convolutional neural network for real-time full profile analysis of big powder diffraction data
title_sort deep convolutional neural network for real-time full profile analysis of big powder diffraction data
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/7adac6f0b28a45c1aa8cd163d3fb007b
work_keys_str_mv AT hongyangdong adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT keithtbutler adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT dorotamatras adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT stephenwtprice adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT yaroslavodarchenko adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT rahulkhatry adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT andrewthompson adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT vesnamiddelkoop adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT simondmjacques adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT andrewmbeale adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT antonisvamvakeros adeepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT hongyangdong deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT keithtbutler deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT dorotamatras deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT stephenwtprice deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT yaroslavodarchenko deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT rahulkhatry deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT andrewthompson deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT vesnamiddelkoop deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT simondmjacques deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT andrewmbeale deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
AT antonisvamvakeros deepconvolutionalneuralnetworkforrealtimefullprofileanalysisofbigpowderdiffractiondata
_version_ 1718385759429328896