Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137611682> ?p ?o ?g. }
- W3137611682 endingPage "110666" @default.
- W3137611682 startingPage "110666" @default.
- W3137611682 abstract "A reduced basis method based on a physics-informed machine learning framework is developed for efficient reduced-order modeling of parametrized partial differential equations (PDEs). A feedforward neural network is used to approximate the mapping from the time-parameter to the reduced coefficients. During the offline stage, the network is trained by minimizing the weighted sum of the residual loss of the reduced-order equations, and the data loss of the labeled reduced coefficients that are obtained via the projection of high-fidelity snapshots onto the reduced space. Such a network is referred to as physics-reinforced neural network (PRNN). As the number of residual points in time-parameter space can be very large, an accurate network – referred to as physics-informed neural network (PINN) – can be trained by minimizing only the residual loss. However, for complex nonlinear problems, the solution of the reduced-order equation is less accurate than the projection of high-fidelity solution onto the reduced space. Therefore, the PRNN trained with the snapshot data is expected to have higher accuracy than the PINN. Numerical results demonstrate that the PRNN is more accurate than the PINN and a purely data-driven neural network for complex problems. During the reduced basis refinement, the PRNN may obtain higher accuracy than the direct reduced-order model based on a Galerkin projection. The online evaluation of PINN/PRNN is orders of magnitude faster than that of the Galerkin reduced-order model." @default.
- W3137611682 created "2021-03-29" @default.
- W3137611682 creator A5037681511 @default.
- W3137611682 creator A5046225712 @default.
- W3137611682 creator A5048257280 @default.
- W3137611682 creator A5074167826 @default.
- W3137611682 date "2021-12-01" @default.
- W3137611682 modified "2023-10-16" @default.
- W3137611682 title "Physics-informed machine learning for reduced-order modeling of nonlinear problems" @default.
- W3137611682 cites W1162707989 @default.
- W3137611682 cites W1969696351 @default.
- W3137611682 cites W1982368110 @default.
- W3137611682 cites W1984516949 @default.
- W3137611682 cites W1994089881 @default.
- W3137611682 cites W2004026774 @default.
- W3137611682 cites W2009447971 @default.
- W3137611682 cites W2033068209 @default.
- W3137611682 cites W2036713095 @default.
- W3137611682 cites W2047591100 @default.
- W3137611682 cites W2049753327 @default.
- W3137611682 cites W2051434435 @default.
- W3137611682 cites W2051994050 @default.
- W3137611682 cites W2076110561 @default.
- W3137611682 cites W2088638050 @default.
- W3137611682 cites W2092398714 @default.
- W3137611682 cites W2097652335 @default.
- W3137611682 cites W2101116262 @default.
- W3137611682 cites W2113794357 @default.
- W3137611682 cites W2117756735 @default.
- W3137611682 cites W2120101088 @default.
- W3137611682 cites W2124138287 @default.
- W3137611682 cites W2124500362 @default.
- W3137611682 cites W2142863015 @default.
- W3137611682 cites W2144954107 @default.
- W3137611682 cites W2147414751 @default.
- W3137611682 cites W2152896489 @default.
- W3137611682 cites W2312884521 @default.
- W3137611682 cites W2334901958 @default.
- W3137611682 cites W2550355449 @default.
- W3137611682 cites W2596697493 @default.
- W3137611682 cites W2618068449 @default.
- W3137611682 cites W2766298346 @default.
- W3137611682 cites W2772709428 @default.
- W3137611682 cites W2791129043 @default.
- W3137611682 cites W2795014364 @default.
- W3137611682 cites W2809491586 @default.
- W3137611682 cites W2810271278 @default.
- W3137611682 cites W2885469054 @default.
- W3137611682 cites W2895892022 @default.
- W3137611682 cites W2899283552 @default.
- W3137611682 cites W2948230027 @default.
- W3137611682 cites W2951128833 @default.
- W3137611682 cites W2951279763 @default.
- W3137611682 cites W2963509795 @default.
- W3137611682 cites W2981433027 @default.
- W3137611682 cites W2986795381 @default.
- W3137611682 cites W2987245967 @default.
- W3137611682 cites W2998104826 @default.
- W3137611682 cites W2998366519 @default.
- W3137611682 cites W3003922491 @default.
- W3137611682 cites W3004113558 @default.
- W3137611682 cites W3011708739 @default.
- W3137611682 cites W3098633050 @default.
- W3137611682 cites W3102429408 @default.
- W3137611682 doi "https://doi.org/10.1016/j.jcp.2021.110666" @default.
- W3137611682 hasPublicationYear "2021" @default.
- W3137611682 type Work @default.
- W3137611682 sameAs 3137611682 @default.
- W3137611682 citedByCount "73" @default.
- W3137611682 countsByYear W31376116822020 @default.
- W3137611682 countsByYear W31376116822021 @default.
- W3137611682 countsByYear W31376116822022 @default.
- W3137611682 countsByYear W31376116822023 @default.
- W3137611682 crossrefType "journal-article" @default.
- W3137611682 hasAuthorship W3137611682A5037681511 @default.
- W3137611682 hasAuthorship W3137611682A5046225712 @default.
- W3137611682 hasAuthorship W3137611682A5048257280 @default.
- W3137611682 hasAuthorship W3137611682A5074167826 @default.
- W3137611682 hasBestOaLocation W31376116821 @default.
- W3137611682 hasConcept C11413529 @default.
- W3137611682 hasConcept C121332964 @default.
- W3137611682 hasConcept C12426560 @default.
- W3137611682 hasConcept C134306372 @default.
- W3137611682 hasConcept C154945302 @default.
- W3137611682 hasConcept C155512373 @default.
- W3137611682 hasConcept C158622935 @default.
- W3137611682 hasConcept C186899397 @default.
- W3137611682 hasConcept C2524010 @default.
- W3137611682 hasConcept C2776459999 @default.
- W3137611682 hasConcept C28826006 @default.
- W3137611682 hasConcept C33923547 @default.
- W3137611682 hasConcept C41008148 @default.
- W3137611682 hasConcept C50644808 @default.
- W3137611682 hasConcept C57493831 @default.
- W3137611682 hasConcept C62520636 @default.
- W3137611682 hasConcept C76155785 @default.
- W3137611682 hasConcept C93779851 @default.
- W3137611682 hasConceptScore W3137611682C11413529 @default.