FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174177148> ?p ?o ?g. }

• W3174177148 endingPage "110526" @default.
• W3174177148 startingPage "110526" @default.
• W3174177148 abstract "This paper presents a new deep learning data-driven model for predicting structure dependent pore-fluid velocity fields in rock. The model is based on a Convolutional Auto-Encoder (CAE) artificial neural network capable of learning from image data generated by direct numerical simulations of fluid flow through pore-structures, such as by Lattice Boltzmann or molecular dynamics methods. The main novelty of the model in comparison to previous CAE-based data-driven approaches consists of three parts. The first is a methodology for decomposing the full-domain of the porous media into sub-regions, or “sub-domains”, in order to reduce the overall size of the CAE, batch process the sub-domains in parallel, and enable the CAE to learn local and generalizable nonlinear mappings of pore-fluid velocities. The second consists of embedding the finite difference solutions of the incompressible Navier-Stokes and continuity equations into convolutional layers prior to the CAE in order to provide the CAE with knowledge of fluid dynamics physics (PhyFlow). The third main novelty is that the training of the CAE is regularized with a hierarchical loss function that encourages the learning of fluid flow patterns (in a way similar to ranked modes in principal component analysis), ranking from most to least important. This is shown to increase the stability in learning, reduce over-fitting, and promote interpretability of the CAE neural network layers (HierCAE). The comprehensive new data-driven model, which we call the PhyFlow-HierCAE model, is shown to exhibit improved accuracy and generalizability of flow field predictions over conventional CAE models, attributable to the embedded physical knowledge and the hierarchical regularization, as well as realize orders of magnitude speed-ups in computation times as a surrogate for the direct numerical simulations. Examples of training and forward predictions on unseen pore-structures are provided and evaluated for data from Lattice Boltzmann and molecular dynamics simulations of pore-fluid flow. The model is shown to be a fast and accurate emulator (or “surrogate”) for predicting effective permeability of unseen pore-structures based on learning from relatively small direct numerical simulation datasets." @default.
• W3174177148 created "2021-07-05" @default.
• W3174177148 creator A5003104055 @default.
• W3174177148 creator A5010192859 @default.
• W3174177148 creator A5021344986 @default.
• W3174177148 creator A5030691366 @default.
• W3174177148 creator A5052676364 @default.
• W3174177148 creator A5059810716 @default.
• W3174177148 creator A5065895042 @default.
• W3174177148 creator A5073783714 @default.
• W3174177148 date "2021-10-01" @default.
• W3174177148 modified "2023-10-16" @default.
• W3174177148 title "A physics-informed and hierarchically regularized data-driven model for predicting fluid flow through porous media" @default.
• W3174177148 cites W1628714285 @default.
• W3174177148 cites W1963588718 @default.
• W3174177148 cites W1966158133 @default.
• W3174177148 cites W1970396657 @default.
• W3174177148 cites W1971966685 @default.
• W3174177148 cites W1980447427 @default.
• W3174177148 cites W1987327282 @default.
• W3174177148 cites W1996204115 @default.
• W3174177148 cites W2010611103 @default.
• W3174177148 cites W2017310369 @default.
• W3174177148 cites W2019465613 @default.
• W3174177148 cites W2031753395 @default.
• W3174177148 cites W2033418788 @default.
• W3174177148 cites W2041949843 @default.
• W3174177148 cites W2046599671 @default.
• W3174177148 cites W2054950515 @default.
• W3174177148 cites W2065626469 @default.
• W3174177148 cites W2065700197 @default.
• W3174177148 cites W2078402834 @default.
• W3174177148 cites W2100495367 @default.
• W3174177148 cites W2111406701 @default.
• W3174177148 cites W2112796928 @default.
• W3174177148 cites W2117242079 @default.
• W3174177148 cites W2124136621 @default.
• W3174177148 cites W2153030457 @default.
• W3174177148 cites W2153513624 @default.
• W3174177148 cites W2261676784 @default.
• W3174177148 cites W2336287975 @default.
• W3174177148 cites W2517872815 @default.
• W3174177148 cites W2535388113 @default.
• W3174177148 cites W2606759614 @default.
• W3174177148 cites W2725890442 @default.
• W3174177148 cites W2757244286 @default.
• W3174177148 cites W2777417212 @default.
• W3174177148 cites W2782666274 @default.
• W3174177148 cites W2899017330 @default.
• W3174177148 cites W2899283552 @default.
• W3174177148 cites W2901021204 @default.
• W3174177148 cites W2907233076 @default.
• W3174177148 cites W2916032760 @default.
• W3174177148 cites W2919115771 @default.
• W3174177148 cites W2949915428 @default.
• W3174177148 cites W2962403043 @default.
• W3174177148 cites W2995587958 @default.
• W3174177148 cites W3003922491 @default.
• W3174177148 cites W3008518994 @default.
• W3174177148 cites W3033526262 @default.
• W3174177148 cites W3047754677 @default.
• W3174177148 doi "https://doi.org/10.1016/j.jcp.2021.110526" @default.
• W3174177148 hasPublicationYear "2021" @default.
• W3174177148 type Work @default.
• W3174177148 sameAs 3174177148 @default.
• W3174177148 citedByCount "18" @default.
• W3174177148 countsByYear W31741771482021 @default.
• W3174177148 countsByYear W31741771482022 @default.
• W3174177148 countsByYear W31741771482023 @default.
• W3174177148 crossrefType "journal-article" @default.
• W3174177148 hasAuthorship W3174177148A5003104055 @default.
• W3174177148 hasAuthorship W3174177148A5010192859 @default.
• W3174177148 hasAuthorship W3174177148A5021344986 @default.
• W3174177148 hasAuthorship W3174177148A5030691366 @default.
• W3174177148 hasAuthorship W3174177148A5052676364 @default.
• W3174177148 hasAuthorship W3174177148A5059810716 @default.
• W3174177148 hasAuthorship W3174177148A5065895042 @default.
• W3174177148 hasAuthorship W3174177148A5073783714 @default.
• W3174177148 hasBestOaLocation W31741771481 @default.
• W3174177148 hasConcept C101738243 @default.
• W3174177148 hasConcept C105569014 @default.
• W3174177148 hasConcept C108583219 @default.
• W3174177148 hasConcept C11413529 @default.
• W3174177148 hasConcept C121332964 @default.
• W3174177148 hasConcept C127413603 @default.
• W3174177148 hasConcept C154945302 @default.
• W3174177148 hasConcept C158622935 @default.
• W3174177148 hasConcept C187320778 @default.
• W3174177148 hasConcept C21821499 @default.
• W3174177148 hasConcept C41008148 @default.
• W3174177148 hasConcept C50644808 @default.
• W3174177148 hasConcept C57879066 @default.
• W3174177148 hasConcept C62520636 @default.
• W3174177148 hasConcept C6648577 @default.
• W3174177148 hasConcept C81363708 @default.
• W3174177148 hasConcept C90278072 @default.
• W3174177148 hasConceptScore W3174177148C101738243 @default.
• W3174177148 hasConceptScore W3174177148C105569014 @default.

• next