Vis enkel innførsel

dc.contributor.authorAhmed, Shady E
dc.contributor.authorSan, Omer
dc.contributor.authorRasheed, Adil
dc.contributor.authorTrian, Iliescu
dc.date.accessioned2022-08-31T15:16:09Z
dc.date.available2022-08-31T15:16:09Z
dc.date.created2021-10-24T00:54:46Z
dc.date.issued2021
dc.identifier.citationPhysics of Fluids. 2021, 33 (12), 121702.en_US
dc.identifier.issn1070-6631
dc.identifier.urihttps://hdl.handle.net/11250/3014766
dc.description.abstractAutoencoder techniques find increasingly common use in reduced order modeling as a means to create a latent space. This reduced order representation offers a modular data-driven modeling approach for nonlinear dynamical systems when integrated with a time series predictive model. In this Letter, we put forth a nonlinear proper orthogonal decomposition (POD) framework, which is an end-to-end Galerkin-free model combining autoencoders with long short-term memory networks for dynamics. By eliminating the projection error due to the truncation of Galerkin models, a key enabler of the proposed nonintrusive approach is the kinematic construction of a nonlinear mapping between the full-rank expansion of the POD coefficients and the latent space where the dynamics evolve. We test our framework for model reduction of a convection-dominated system, which is generally challenging for reduced order models. Our approach not only improves the accuracy, but also significantly reduces the computational cost of training and testing. This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research under Award Number DE-SC0019290. O.S. gratefully acknowledges the Early Career Research Program (ECRP) support of the U.S. Department of Energy. O.S. also gratefully acknowledges the financial support of the National Science Foundation under Award No. DMS-2012255. T.I. acknowledges support through National Science Foundation Grant No. DMS-2012253.en_US
dc.language.isoengen_US
dc.publisherAmerican Institute of Physicsen_US
dc.subjectReduced order modelsen_US
dc.subjectData-driven modelingen_US
dc.subjectAutoencodersen_US
dc.subjectLong short-term memory networksen_US
dc.titleNonlinear proper orthogonal decomposition for convection-dominated flowsen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionacceptedVersionen_US
dc.source.volume33en_US
dc.source.journalPhysics of Fluidsen_US
dc.source.issue12en_US
dc.identifier.doi10.1063/5.0074310
dc.identifier.cristin1948001
dc.source.articlenumber121702en_US
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode2


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel