001024403 001__ 1024403
001024403 005__ 20250204113820.0
001024403 0247_ $$2doi$$a10.3390/fluids9040084
001024403 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-02146
001024403 0247_ $$2WOS$$aWOS:001211140400001
001024403 037__ $$aFZJ-2024-02146
001024403 041__ $$aEnglish
001024403 082__ $$a530
001024403 1001_ $$0P:(DE-HGF)0$$aHassanian, Reza$$b0$$eCorresponding author
001024403 245__ $$aTurbulent Flow Prediction-Simulation: Strained Flow with Initial Isotropic Condition Using a GRU Model Trained by an Experimental Lagrangian Framework, with Emphasis on Hyperparameter Optimization
001024403 260__ $$aBelgrade$$bMDPI$$c2024
001024403 3367_ $$2DRIVER$$aarticle
001024403 3367_ $$2DataCite$$aOutput Types/Journal article
001024403 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1712138240_21538
001024403 3367_ $$2BibTeX$$aARTICLE
001024403 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001024403 3367_ $$00$$2EndNote$$aJournal Article
001024403 500__ $$aThe paper is available open-access on the publisher website.
001024403 520__ $$aThis study presents a novel approach to using a gated recurrent unit (GRU) model, a deep neural network, to predict turbulent flows in a Lagrangian framework. The emerging velocity field is predicted based on experimental data from a strained turbulent flow, which was initially a nearly homogeneous isotropic turbulent flow at the measurement area. The distorted turbulent flow has a Taylor microscale Reynolds number in the range of 100 < Re_\lamda < 152 before creating the strain and is strained with a mean strain rate of 4 s^−1 in the Y direction. The measurement is conducted in the presence of gravity consequent to the actual condition, an effect that is usually neglected and has not been investigated in most numerical studies. A Lagrangian particle tracking technique is used to extract the flow characterizations. It is used to assess the capability of the GRU model to forecast the unknown turbulent flow pattern affected by distortion and gravity using spatiotemporal input data. Using the flow track’s location (spatial) and time (temporal) highlights the model’s superiority. The suggested approach provides the possibility to predict the emerging pattern of the strained turbulent flow properties observed in many natural and artificial phenomena. In order to optimize the consumed computing, hyperparameter optimization (HPO) is used to improve the GRU model performance by 14–20%. Model training and inference run on the high-performance computing (HPC) JUWELS-BOOSTER and DEEP-DAM systems at the Jülich Supercomputing Centre, and the code speed-up on these machines is measured. The proposed model produces accurate predictions for turbulent flows in the Lagrangian view with a mean absolute error (MAE) of 0.001 and an R^2 score of 0.993.
001024403 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001024403 536__ $$0G:(EU-Grant)951733$$aRAISE - Research on AI- and Simulation-Based Engineering at Exascale (951733)$$c951733$$fH2020-INFRAEDI-2019-1$$x1
001024403 536__ $$0G:(DE-Juel-1)DEA02266$$aEUROCC-2 (DEA02266)$$cDEA02266$$x2
001024403 588__ $$aDataset connected to DataCite
001024403 7001_ $$0P:(DE-Juel1)180916$$aAach, Marcel$$b1$$ufzj
001024403 7001_ $$0P:(DE-Juel1)165948$$aLintermann, Andreas$$b2$$ufzj
001024403 7001_ $$0P:(DE-HGF)0$$aHelgadóttir, Ásdís$$b3
001024403 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b4$$ufzj
001024403 773__ $$0PERI:(DE-600)2882362-X$$a10.3390/fluids9040084$$gVol. 9, no. 4, p. 84 -$$n4$$p84$$tFluids$$v9$$x2311-5521$$y2024
001024403 8564_ $$uhttps://www.mdpi.com/2311-5521/9/4/84
001024403 8564_ $$uhttps://juser.fz-juelich.de/record/1024403/files/fluids-09-00084.pdf$$yOpenAccess
001024403 8564_ $$uhttps://juser.fz-juelich.de/record/1024403/files/fluids-09-00084.gif?subformat=icon$$xicon$$yOpenAccess
001024403 8564_ $$uhttps://juser.fz-juelich.de/record/1024403/files/fluids-09-00084.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001024403 8564_ $$uhttps://juser.fz-juelich.de/record/1024403/files/fluids-09-00084.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001024403 8564_ $$uhttps://juser.fz-juelich.de/record/1024403/files/fluids-09-00084.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001024403 909CO $$ooai:juser.fz-juelich.de:1024403$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
001024403 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180916$$aForschungszentrum Jülich$$b1$$kFZJ
001024403 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165948$$aForschungszentrum Jülich$$b2$$kFZJ
001024403 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b4$$kFZJ
001024403 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001024403 9141_ $$y2024
001024403 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001024403 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2023-10-27
001024403 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001024403 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2023-10-27
001024403 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-03
001024403 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-03
001024403 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-04-10T15:28:06Z
001024403 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-04-10T15:28:06Z
001024403 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-04-10T15:28:06Z
001024403 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-03
001024403 915__ $$0StatID:(DE-HGF)0112$$2StatID$$aWoS$$bEmerging Sources Citation Index$$d2025-01-03
001024403 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-03
001024403 920__ $$lyes
001024403 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001024403 980__ $$ajournal
001024403 980__ $$aVDB
001024403 980__ $$aUNRESTRICTED
001024403 980__ $$aI:(DE-Juel1)JSC-20090406
001024403 9801_ $$aFullTexts