000859970 001__ 859970
000859970 005__ 20210511092514.0
000859970 020__ $$a978-3-030-02464-2 (print)
000859970 020__ $$a978-3-030-02465-9 (electronic)
000859970 0247_ $$2doi$$a10.1007/978-3-030-02465-9_44
000859970 0247_ $$2ISSN$$a0302-9743
000859970 0247_ $$2ISSN$$a1611-3349
000859970 0247_ $$2WOS$$aWOS:000612998200051
000859970 037__ $$aFZJ-2019-00776
000859970 1001_ $$00000-0001-9922-9742$$aBode, Mathis$$b0
000859970 1112_ $$aInternational Conference on High Performance Computing$$cFrankfurt$$d2018-06-24 - 2018-06-28$$wGermany
000859970 245__ $$aTowards Prediction of Turbulent Flows at High Reynolds Numbers Using High Performance Computing Data and Deep Learning
000859970 260__ $$aCham$$bSpringer International Publishing$$c2018
000859970 29510 $$aHigh Performance Computing
000859970 300__ $$a614 - 623
000859970 3367_ $$2ORCID$$aCONFERENCE_PAPER
000859970 3367_ $$033$$2EndNote$$aConference Paper
000859970 3367_ $$2BibTeX$$aINPROCEEDINGS
000859970 3367_ $$2DRIVER$$aconferenceObject
000859970 3367_ $$2DataCite$$aOutput Types/Conference Paper
000859970 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1620717880_29207
000859970 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000859970 4900_ $$aLecture Notes in Computer Science$$v11203
000859970 520__ $$aIn this paper, deep learning (DL) methods are evaluated in the context of turbulent flows. Various generative adversarial networks (GANs) are discussed with respect to their suitability for understanding and modeling turbulence. Wasserstein GANs (WGANs) are then chosen to generate small-scale turbulence. Highly resolved direct numerical simulation (DNS) turbulent data is used for training the WGANs and the effect of network parameters, such as learning rate and loss function, is studied. Qualitatively good agreement between DNS input data and generated turbulent structures is shown. A quantitative statistical assessment of the predicted turbulent fields is performed.
000859970 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x0
000859970 536__ $$0G:(DE-Juel1)jhpc55_20180501$$aUsing deep learning to predict statistics of turbulent flows at high Reynolds numbers (jhpc55_20180501)$$cjhpc55_20180501$$fUsing deep learning to predict statistics of turbulent flows at high Reynolds numbers$$x1
000859970 588__ $$aDataset connected to CrossRef Book Series
000859970 7001_ $$00000-0003-0038-5249$$aGauding, Michael$$b1$$eCorresponding author
000859970 7001_ $$0P:(DE-Juel1)168541$$aGöbbert, Jens Henrik$$b2
000859970 7001_ $$00000-0001-8335-4573$$aLiao, Baohao$$b3
000859970 7001_ $$0P:(DE-Juel1)158080$$aJitsev, Jenia$$b4
000859970 7001_ $$00000-0001-5656-0961$$aPitsch, Heinz$$b5
000859970 770__ $$aISC High Performance 2018 International Workshops
000859970 773__ $$a10.1007/978-3-030-02465-9_44
000859970 909CO $$ooai:juser.fz-juelich.de:859970$$pVDB
000859970 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)168541$$aForschungszentrum Jülich$$b2$$kFZJ
000859970 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)158080$$aForschungszentrum Jülich$$b4$$kFZJ
000859970 9131_ $$0G:(DE-HGF)POF3-511$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vComputational Science and Mathematical Methods$$x0
000859970 9132_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000859970 9141_ $$y2018
000859970 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz
000859970 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000859970 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000859970 980__ $$acontrib
000859970 980__ $$aVDB
000859970 980__ $$acontb
000859970 980__ $$aI:(DE-Juel1)JSC-20090406
000859970 980__ $$aUNRESTRICTED