Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287329996> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4287329996 abstract "The permeability of complex porous materials can be obtained via direct flow simulation, which provides the most accurate results, but is very computationally expensive. In particular, the simulation convergence time scales poorly as simulation domains become tighter or more heterogeneous. Semi-analytical models that rely on averaged structural properties (i.e. porosity and tortuosity) have been proposed, but these features only summarize the domain, resulting in limited applicability. On the other hand, data-driven machine learning approaches have shown great promise for building more general models by virtue of accounting for the spatial arrangement of the domains solid boundaries. However, prior approaches building on the Convolutional Neural Network (ConvNet) literature concerning 2D image recognition problems do not scale well to the large 3D domains required to obtain a Representative Elementary Volume (REV). As such, most prior work focused on homogeneous samples, where a small REV entails that that the global nature of fluid flow could be mostly neglected, and accordingly, the memory bottleneck of addressing 3D domains with ConvNets was side-stepped. Therefore, important geometries such as fractures and vuggy domains could not be well-modeled. In this work, we address this limitation with a general multiscale deep learning model that is able to learn from porous media simulation data. By using a coupled set of neural networks that view the domain on different scales, we enable the evaluation of large images in approximately one second on a single Graphics Processing Unit. This model architecture opens up the possibility of modeling domain sizes that would not be feasible using traditional direct simulation tools on a desktop computer." @default.
- W4287329996 created "2022-07-25" @default.
- W4287329996 creator A5021344986 @default.
- W4287329996 creator A5023112770 @default.
- W4287329996 creator A5046042599 @default.
- W4287329996 creator A5055112597 @default.
- W4287329996 creator A5059810716 @default.
- W4287329996 creator A5061933200 @default.
- W4287329996 creator A5061964004 @default.
- W4287329996 creator A5073783714 @default.
- W4287329996 creator A5076601235 @default.
- W4287329996 date "2021-02-10" @default.
- W4287329996 modified "2023-10-16" @default.
- W4287329996 title "Computationally Efficient Multiscale Neural Networks Applied To Fluid Flow In Complex 3D Porous Media" @default.
- W4287329996 doi "https://doi.org/10.48550/arxiv.2102.07625" @default.
- W4287329996 hasPublicationYear "2021" @default.
- W4287329996 type Work @default.
- W4287329996 citedByCount "0" @default.
- W4287329996 crossrefType "posted-content" @default.
- W4287329996 hasAuthorship W4287329996A5021344986 @default.
- W4287329996 hasAuthorship W4287329996A5023112770 @default.
- W4287329996 hasAuthorship W4287329996A5046042599 @default.
- W4287329996 hasAuthorship W4287329996A5055112597 @default.
- W4287329996 hasAuthorship W4287329996A5059810716 @default.
- W4287329996 hasAuthorship W4287329996A5061933200 @default.
- W4287329996 hasAuthorship W4287329996A5061964004 @default.
- W4287329996 hasAuthorship W4287329996A5073783714 @default.
- W4287329996 hasAuthorship W4287329996A5076601235 @default.
- W4287329996 hasBestOaLocation W42873299961 @default.
- W4287329996 hasConcept C105569014 @default.
- W4287329996 hasConcept C108583219 @default.
- W4287329996 hasConcept C119857082 @default.
- W4287329996 hasConcept C121332964 @default.
- W4287329996 hasConcept C127313418 @default.
- W4287329996 hasConcept C134306372 @default.
- W4287329996 hasConcept C135628077 @default.
- W4287329996 hasConcept C149635348 @default.
- W4287329996 hasConcept C154945302 @default.
- W4287329996 hasConcept C160635147 @default.
- W4287329996 hasConcept C173608175 @default.
- W4287329996 hasConcept C185250623 @default.
- W4287329996 hasConcept C187320778 @default.
- W4287329996 hasConcept C2778755073 @default.
- W4287329996 hasConcept C2779851693 @default.
- W4287329996 hasConcept C2780513914 @default.
- W4287329996 hasConcept C33923547 @default.
- W4287329996 hasConcept C36503486 @default.
- W4287329996 hasConcept C41008148 @default.
- W4287329996 hasConcept C50644808 @default.
- W4287329996 hasConcept C62520636 @default.
- W4287329996 hasConcept C6648577 @default.
- W4287329996 hasConcept C81363708 @default.
- W4287329996 hasConcept C97355855 @default.
- W4287329996 hasConceptScore W4287329996C105569014 @default.
- W4287329996 hasConceptScore W4287329996C108583219 @default.
- W4287329996 hasConceptScore W4287329996C119857082 @default.
- W4287329996 hasConceptScore W4287329996C121332964 @default.
- W4287329996 hasConceptScore W4287329996C127313418 @default.
- W4287329996 hasConceptScore W4287329996C134306372 @default.
- W4287329996 hasConceptScore W4287329996C135628077 @default.
- W4287329996 hasConceptScore W4287329996C149635348 @default.
- W4287329996 hasConceptScore W4287329996C154945302 @default.
- W4287329996 hasConceptScore W4287329996C160635147 @default.
- W4287329996 hasConceptScore W4287329996C173608175 @default.
- W4287329996 hasConceptScore W4287329996C185250623 @default.
- W4287329996 hasConceptScore W4287329996C187320778 @default.
- W4287329996 hasConceptScore W4287329996C2778755073 @default.
- W4287329996 hasConceptScore W4287329996C2779851693 @default.
- W4287329996 hasConceptScore W4287329996C2780513914 @default.
- W4287329996 hasConceptScore W4287329996C33923547 @default.
- W4287329996 hasConceptScore W4287329996C36503486 @default.
- W4287329996 hasConceptScore W4287329996C41008148 @default.
- W4287329996 hasConceptScore W4287329996C50644808 @default.
- W4287329996 hasConceptScore W4287329996C62520636 @default.
- W4287329996 hasConceptScore W4287329996C6648577 @default.
- W4287329996 hasConceptScore W4287329996C81363708 @default.
- W4287329996 hasConceptScore W4287329996C97355855 @default.
- W4287329996 hasLocation W42873299961 @default.
- W4287329996 hasOpenAccess W4287329996 @default.
- W4287329996 hasPrimaryLocation W42873299961 @default.
- W4287329996 hasRelatedWork W2337926734 @default.
- W4287329996 hasRelatedWork W2799614062 @default.
- W4287329996 hasRelatedWork W3003770199 @default.
- W4287329996 hasRelatedWork W3136076031 @default.
- W4287329996 hasRelatedWork W3173182854 @default.
- W4287329996 hasRelatedWork W4281780675 @default.
- W4287329996 hasRelatedWork W4285586943 @default.
- W4287329996 hasRelatedWork W4287329996 @default.
- W4287329996 hasRelatedWork W4287776258 @default.
- W4287329996 hasRelatedWork W3009789068 @default.
- W4287329996 isParatext "false" @default.
- W4287329996 isRetracted "false" @default.
- W4287329996 workType "article" @default.