000888899 001__ 888899
000888899 005__ 20210130011157.0
000888899 0247_ $$2arXiv$$aarXiv:2010.07634
000888899 0247_ $$2Handle$$a2128/26611
000888899 0247_ $$2altmetric$$aaltmetric:92471027
000888899 037__ $$aFZJ-2020-05304
000888899 1001_ $$0P:(DE-HGF)0$$aCarmona-Loaiza, Juan Manuel$$b0$$eCorresponding author
000888899 245__ $$aTowards Reflectivity profile inversion through Artificial Neural Networks
000888899 260__ $$c2020
000888899 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1609248341_12842
000888899 3367_ $$2ORCID$$aWORKING_PAPER
000888899 3367_ $$028$$2EndNote$$aElectronic Article
000888899 3367_ $$2DRIVER$$apreprint
000888899 3367_ $$2BibTeX$$aARTICLE
000888899 3367_ $$2DataCite$$aOutput Types/Working Paper
000888899 500__ $$aSubmitted to MLST (Machine Learning: Science and Technology) - 10 pages, 8 figures
000888899 520__ $$aThe goal of Specular Neutron and X-ray Reflectometry is to infer materials Scattering Length Density (SLD) profiles from experimental reflectivity curves. This paper focuses on investigating an original approach to the ill-posed non-invertible problem which involves the use of Artificial Neural Networks (ANN). In particular, the numerical experiments described here deal with large data sets of simulated reflectivity curves and SLD profiles, and aim to assess the applicability of Data Science and Machine Learning technology to the analysis of data generated at large scale facilities. It is demonstrated that, under certain circumstances, properly trained Deep Neural Networks are capable of correctly recovering plausible SLD profiles when presented with never-seen-before simulated reflectivity curves. When the necessary conditions are met, a proper implementation of the described approach would offer two main advantages over traditional fitting methods when dealing with real experiments, namely, 1. no prior assumptions about the sample physical model are required and 2. the times-to-solution are shrank by orders of magnitude, enabling faster batch analyses for large datasets.
000888899 536__ $$0G:(DE-HGF)POF3-6G4$$a6G4 - Jülich Centre for Neutron Research (JCNS) (POF3-623)$$cPOF3-623$$fPOF III$$x0
000888899 536__ $$0G:(DE-HGF)POF3-6G15$$a6G15 - FRM II / MLZ (POF3-6G15)$$cPOF3-6G15$$fPOF III$$x1
000888899 588__ $$aDataset connected to arXivarXiv
000888899 65027 $$0V:(DE-MLZ)SciArea-220$$2V:(DE-HGF)$$aInstrument and Method Development$$x0
000888899 65017 $$0V:(DE-MLZ)GC-2003-2016$$2V:(DE-HGF)$$aOthers$$x0
000888899 693__ $$0EXP:(DE-MLZ)NOSPEC-20140101$$5EXP:(DE-MLZ)NOSPEC-20140101$$eNo specific instrument$$x0
000888899 8564_ $$uhttps://arxiv.org/abs/2010.07634
000888899 8564_ $$uhttps://juser.fz-juelich.de/record/888899/files/Neural%20Networks%20for%20Reflectometry.pdf$$yOpenAccess
000888899 909CO $$ooai:juser.fz-juelich.de:888899$$pdnbdelivery$$pVDB$$pVDB:MLZ$$pdriver$$popen_access$$popenaire
000888899 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-HGF)0$$aForschungszentrum Jülich$$b0$$kFZJ
000888899 9131_ $$0G:(DE-HGF)POF3-623$$1G:(DE-HGF)POF3-620$$2G:(DE-HGF)POF3-600$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF3-6G4$$aDE-HGF$$bForschungsbereich Materie$$lVon Materie zu Materialien und Leben$$vFacility topic: Neutrons for Research on Condensed Matter$$x0
000888899 9131_ $$0G:(DE-HGF)POF3-6G15$$1G:(DE-HGF)POF3-6G0$$2G:(DE-HGF)POF3-600$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF3-6G15$$aDE-HGF$$bForschungsbereich Materie$$lGroßgeräte: Materie$$vFRM II / MLZ$$x1
000888899 9141_ $$y2020
000888899 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000888899 920__ $$lyes
000888899 9201_ $$0I:(DE-Juel1)JCNS-FRM-II-20110218$$kJCNS-FRM-II$$lJCNS-FRM-II$$x0
000888899 9201_ $$0I:(DE-588b)4597118-3$$kMLZ$$lHeinz Maier-Leibnitz Zentrum$$x1
000888899 980__ $$apreprint
000888899 980__ $$aVDB
000888899 980__ $$aUNRESTRICTED
000888899 980__ $$aI:(DE-Juel1)JCNS-FRM-II-20110218
000888899 980__ $$aI:(DE-588b)4597118-3
000888899 9801_ $$aFullTexts