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

作     者：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 

作者机构：Department of ChemistryUniversity College London20 Gordon StreetLondon WC1H 0AJUnited Kingdom SciMLScientific Computer DivisionSTFCRutherford Appleton LaboratoryHarwell OX110QXUnited Kingdom Finden LimitedMerchant House5 East St Helens StreetAbingdon OX145EGUnited Kingdom National Physical LaboratoryHampton RoadTeddington TW110LWUnited Kingdom Flemish Institute for Technological ResearchVITO NVBoeretang 200Mol 2400Belgium Research Complex at HarwellRutherford Appleton LaboratoryHarwell Science and Innovation CampusDidcotOX110FA OxfordshireUnited Kingdom Present address:Diamond Light SourceHarwell Science and Innovation CampusDidcotOxfordshire OX110DEUnited Kingdom Present address:The Faraday InstitutionQuad OneHarwell Science and Innovation CampusOX110RA OxfordshireUnited Kingdom 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2021年第7卷第1期

页      面：671-679页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：We would like to thank Marco di Michiel(ID15A,ESRF)and Jakub Drnec(ID31,ESRF)for preparing beamline instrumentation and setup and for their help with the experimental XRD-CT data acquisition.We acknowledge ESRF for beamtime.Finden acknowledges funding through the Innovate UK Analysis for Innovators(A4i)program(Project No:106107) A.M.B.acknowledges EPSRC(grants EP/R026815/1 and EP/S016481/1) 

主　　题：network powder analysis 

摘      要：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 *** 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/CeO_(2)-ZrO_(2)/Al_(2)O_(3) catalytic material system consisting of ca.20,000 diffraction *** 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 *** main advantage of PQNet 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.