Matches in SemOpenAlex for { <https://semopenalex.org/work/W3082768732> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3082768732 abstract "Inverse problems in fluid dynamics are ubiquitous in science and engineering, with applications ranging from electronic cooling system design to ocean modeling. We propose a general and robust approach for solving inverse problems in the steady-state Navier-Stokes equations by combining deep neural networks and numerical partial differential equation (PDE) schemes. Our approach expresses numerical simulation as a computational graph with differentiable operators. We then solve inverse problems by constrained optimization, using gradients calculated from the computational graph with reverse-mode automatic differentiation. This technique enables us to model unknown physical properties using deep neural networks and embed them into the PDE model. We demonstrate the effectiveness of our method by computing spatially-varying viscosity and conductivity fields with deep neural networks (DNNs) and training the DNNs using partial observations of velocity fields. We show that the DNNs are capable of modeling complex spatially-varying physical fields with sparse and noisy data. Our implementation leverages the open access ADCME, a library for solving inverse modeling problems in scientific computing using automatic differentiation." @default.
- W3082768732 created "2020-09-08" @default.
- W3082768732 creator A5046131163 @default.
- W3082768732 creator A5055150226 @default.
- W3082768732 creator A5061822097 @default.
- W3082768732 creator A5062619631 @default.
- W3082768732 date "2020-08-29" @default.
- W3082768732 modified "2023-09-26" @default.
- W3082768732 title "Solving Inverse Problems in Steady-State Navier-Stokes Equations using Deep Neural Networks" @default.
- W3082768732 cites W1528439235 @default.
- W3082768732 cites W1991207528 @default.
- W3082768732 cites W2051434435 @default.
- W3082768732 cites W2066012686 @default.
- W3082768732 cites W2081612620 @default.
- W3082768732 cites W2337514662 @default.
- W3082768732 cites W2749028154 @default.
- W3082768732 cites W2771305881 @default.
- W3082768732 cites W2962727772 @default.
- W3082768732 cites W2989994628 @default.
- W3082768732 cites W3007740214 @default.
- W3082768732 cites W3022973855 @default.
- W3082768732 cites W3082908155 @default.
- W3082768732 cites W3102436560 @default.
- W3082768732 cites W3105469151 @default.
- W3082768732 doi "https://doi.org/10.48550/arxiv.2008.13074" @default.
- W3082768732 hasPublicationYear "2020" @default.
- W3082768732 type Work @default.
- W3082768732 sameAs 3082768732 @default.
- W3082768732 citedByCount "3" @default.
- W3082768732 countsByYear W30827687322020 @default.
- W3082768732 countsByYear W30827687322021 @default.
- W3082768732 crossrefType "posted-content" @default.
- W3082768732 hasAuthorship W3082768732A5046131163 @default.
- W3082768732 hasAuthorship W3082768732A5055150226 @default.
- W3082768732 hasAuthorship W3082768732A5061822097 @default.
- W3082768732 hasAuthorship W3082768732A5062619631 @default.
- W3082768732 hasBestOaLocation W30827687321 @default.
- W3082768732 hasConcept C11413529 @default.
- W3082768732 hasConcept C126255220 @default.
- W3082768732 hasConcept C133512626 @default.
- W3082768732 hasConcept C134306372 @default.
- W3082768732 hasConcept C135252773 @default.
- W3082768732 hasConcept C154945302 @default.
- W3082768732 hasConcept C202615002 @default.
- W3082768732 hasConcept C207467116 @default.
- W3082768732 hasConcept C2524010 @default.
- W3082768732 hasConcept C28826006 @default.
- W3082768732 hasConcept C2984842247 @default.
- W3082768732 hasConcept C33923547 @default.
- W3082768732 hasConcept C41008148 @default.
- W3082768732 hasConcept C45374587 @default.
- W3082768732 hasConcept C50644808 @default.
- W3082768732 hasConcept C93779851 @default.
- W3082768732 hasConceptScore W3082768732C11413529 @default.
- W3082768732 hasConceptScore W3082768732C126255220 @default.
- W3082768732 hasConceptScore W3082768732C133512626 @default.
- W3082768732 hasConceptScore W3082768732C134306372 @default.
- W3082768732 hasConceptScore W3082768732C135252773 @default.
- W3082768732 hasConceptScore W3082768732C154945302 @default.
- W3082768732 hasConceptScore W3082768732C202615002 @default.
- W3082768732 hasConceptScore W3082768732C207467116 @default.
- W3082768732 hasConceptScore W3082768732C2524010 @default.
- W3082768732 hasConceptScore W3082768732C28826006 @default.
- W3082768732 hasConceptScore W3082768732C2984842247 @default.
- W3082768732 hasConceptScore W3082768732C33923547 @default.
- W3082768732 hasConceptScore W3082768732C41008148 @default.
- W3082768732 hasConceptScore W3082768732C45374587 @default.
- W3082768732 hasConceptScore W3082768732C50644808 @default.
- W3082768732 hasConceptScore W3082768732C93779851 @default.
- W3082768732 hasLocation W30827687321 @default.
- W3082768732 hasOpenAccess W3082768732 @default.
- W3082768732 hasPrimaryLocation W30827687321 @default.
- W3082768732 hasRelatedWork W1484651240 @default.
- W3082768732 hasRelatedWork W1977221000 @default.
- W3082768732 hasRelatedWork W2034739874 @default.
- W3082768732 hasRelatedWork W2678028941 @default.
- W3082768732 hasRelatedWork W2779338154 @default.
- W3082768732 hasRelatedWork W3118927209 @default.
- W3082768732 hasRelatedWork W3199540457 @default.
- W3082768732 hasRelatedWork W4290420357 @default.
- W3082768732 hasRelatedWork W4317837976 @default.
- W3082768732 hasRelatedWork W4366317372 @default.
- W3082768732 isParatext "false" @default.
- W3082768732 isRetracted "false" @default.
- W3082768732 magId "3082768732" @default.
- W3082768732 workType "article" @default.