Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287904976> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4287904976 abstract "Traditional reduced order modeling techniques such as the reduced basis (RB) method (relying, e.g., on proper orthogonal decomposition (POD)) suffer from severe limitations when dealing with nonlinear time-dependent parametrized PDEs, because of the fundamental assumption of linear superimposition of modes they are based on. For this reason, in the case of problems featuring coherent structures that propagate over time such as transport, wave, or convection-dominated phenomena, the RB method usually yields inefficient reduced order models (ROMs) if one aims at obtaining reduced order approximations sufficiently accurate compared to the high-fidelity, full order model (FOM) solution. To overcome these limitations, in this work, we propose a new nonlinear approach to set reduced order models by exploiting deep learning (DL) algorithms. In the resulting nonlinear ROM, which we refer to as DL-ROM, both the nonlinear trial manifold (corresponding to the set of basis functions in a linear ROM) as well as the nonlinear reduced dynamics (corresponding to the projection stage in a linear ROM) are learned in a non-intrusive way by relying on DL algorithms; the latter are trained on a set of FOM solutions obtained for different parameter values. In this paper, we show how to construct a DL-ROM for both linear and nonlinear time-dependent parametrized PDEs; moreover, we assess its accuracy on test cases featuring different parametrized PDE problems. Numerical results indicate that DL-ROMs whose dimension is equal to the intrinsic dimensionality of the PDE solutions manifold are able to approximate the solution of parametrized PDEs in situations where a huge number of POD modes would be necessary to achieve the same degree of accuracy." @default.
- W4287904976 created "2022-07-26" @default.
- W4287904976 creator A5034191028 @default.
- W4287904976 creator A5040645637 @default.
- W4287904976 creator A5082126056 @default.
- W4287904976 date "2020-01-12" @default.
- W4287904976 modified "2023-10-13" @default.
- W4287904976 title "A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs" @default.
- W4287904976 doi "https://doi.org/10.48550/arxiv.2001.04001" @default.
- W4287904976 hasPublicationYear "2020" @default.
- W4287904976 type Work @default.
- W4287904976 citedByCount "0" @default.
- W4287904976 crossrefType "posted-content" @default.
- W4287904976 hasAuthorship W4287904976A5034191028 @default.
- W4287904976 hasAuthorship W4287904976A5040645637 @default.
- W4287904976 hasAuthorship W4287904976A5082126056 @default.
- W4287904976 hasBestOaLocation W42879049761 @default.
- W4287904976 hasConcept C111030470 @default.
- W4287904976 hasConcept C11413529 @default.
- W4287904976 hasConcept C121332964 @default.
- W4287904976 hasConcept C12426560 @default.
- W4287904976 hasConcept C126255220 @default.
- W4287904976 hasConcept C127413603 @default.
- W4287904976 hasConcept C134306372 @default.
- W4287904976 hasConcept C154945302 @default.
- W4287904976 hasConcept C158622935 @default.
- W4287904976 hasConcept C177264268 @default.
- W4287904976 hasConcept C199360897 @default.
- W4287904976 hasConcept C202444582 @default.
- W4287904976 hasConcept C2524010 @default.
- W4287904976 hasConcept C28826006 @default.
- W4287904976 hasConcept C33676613 @default.
- W4287904976 hasConcept C33923547 @default.
- W4287904976 hasConcept C41008148 @default.
- W4287904976 hasConcept C529865628 @default.
- W4287904976 hasConcept C57493831 @default.
- W4287904976 hasConcept C5917680 @default.
- W4287904976 hasConcept C62520636 @default.
- W4287904976 hasConcept C70518039 @default.
- W4287904976 hasConcept C78519656 @default.
- W4287904976 hasConceptScore W4287904976C111030470 @default.
- W4287904976 hasConceptScore W4287904976C11413529 @default.
- W4287904976 hasConceptScore W4287904976C121332964 @default.
- W4287904976 hasConceptScore W4287904976C12426560 @default.
- W4287904976 hasConceptScore W4287904976C126255220 @default.
- W4287904976 hasConceptScore W4287904976C127413603 @default.
- W4287904976 hasConceptScore W4287904976C134306372 @default.
- W4287904976 hasConceptScore W4287904976C154945302 @default.
- W4287904976 hasConceptScore W4287904976C158622935 @default.
- W4287904976 hasConceptScore W4287904976C177264268 @default.
- W4287904976 hasConceptScore W4287904976C199360897 @default.
- W4287904976 hasConceptScore W4287904976C202444582 @default.
- W4287904976 hasConceptScore W4287904976C2524010 @default.
- W4287904976 hasConceptScore W4287904976C28826006 @default.
- W4287904976 hasConceptScore W4287904976C33676613 @default.
- W4287904976 hasConceptScore W4287904976C33923547 @default.
- W4287904976 hasConceptScore W4287904976C41008148 @default.
- W4287904976 hasConceptScore W4287904976C529865628 @default.
- W4287904976 hasConceptScore W4287904976C57493831 @default.
- W4287904976 hasConceptScore W4287904976C5917680 @default.
- W4287904976 hasConceptScore W4287904976C62520636 @default.
- W4287904976 hasConceptScore W4287904976C70518039 @default.
- W4287904976 hasConceptScore W4287904976C78519656 @default.
- W4287904976 hasLocation W42879049761 @default.
- W4287904976 hasLocation W42879049762 @default.
- W4287904976 hasOpenAccess W4287904976 @default.
- W4287904976 hasPrimaryLocation W42879049761 @default.
- W4287904976 hasRelatedWork W2056704125 @default.
- W4287904976 hasRelatedWork W2146552914 @default.
- W4287904976 hasRelatedWork W2242039446 @default.
- W4287904976 hasRelatedWork W2783398459 @default.
- W4287904976 hasRelatedWork W2784058392 @default.
- W4287904976 hasRelatedWork W3089240690 @default.
- W4287904976 hasRelatedWork W3102547816 @default.
- W4287904976 hasRelatedWork W3158813297 @default.
- W4287904976 hasRelatedWork W4287691910 @default.
- W4287904976 hasRelatedWork W2155146656 @default.
- W4287904976 isParatext "false" @default.
- W4287904976 isRetracted "false" @default.
- W4287904976 workType "article" @default.