Adaptive sampling for nonlinear dimensionality reduction based on manifold learning

Publikation: Forskning - peer reviewKonferencebidrag i proceedings

Dokumenter

Vis graf over relationer

We make use of the non-intrusive dimensionality reduction method Isomap in order to emulate nonlinear parametric flow problems that are governed by the Reynolds-averaged Navier-Stokes equations. Isomap is a manifold learning approach that provides a low-dimensional embedding space that is approximately isometric to the manifold that is assumed to be formed by the high-fidelity Navier-Stokes flow solutions under smooth variations of the inflow conditions. The focus of the work at hand is the adaptive construction and refinement of the Isomap emulator: We exploit the non-Euclidean Isomap metric to detect and fill up gaps in the sampling in the embedding space. The performance of the proposed manifold filling method will be illustrated by numerical experiments, where we consider nonlinear parameter-dependent steady-state Navier-Stokes flows in the transonic regime.
OriginalsprogEngelsk
TitelModel Reduction of Parametrized Systems III : The special volume in MS&A series, edited by Springer.
Antal sider15
UdgiverSpringer
Publikationsdato2017
Sider1-15
Artikelnummer22
StatusUdgivet - 2017
Begivenhed - Trieste, Italien

Konference

KonferenceModel Reduction of Parametrized Systems III
LokationSISSA
LandItalien
ByTrieste
Periode13/10/201516/10/2015
Internetadresse

Download statistik

Ingen data tilgængelig