Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043504355> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3043504355 endingPage "104676" @default.
- W3043504355 startingPage "104676" @default.
- W3043504355 abstract "Geological parameterization enables the representation of geomodels in terms of a relatively small set of variables. Parameterization is therefore very useful in the context of data assimilation and uncertainty quantification. In this study, a deep-learning-based geological parameterization algorithm, CNN-PCA, is developed for complex 3D geomodels. CNN-PCA entails the use of convolutional neural networks as a post-processor for the low-dimensional principal component analysis representation of a geomodel. The 3D treatments presented here differ somewhat from those used in the 2D CNN-PCA procedure. Specifically, we introduce a new supervised-learning-based reconstruction loss, which is used in combination with style loss and hard data loss. The style loss uses features extracted from a 3D CNN pretrained for video classification. The 3D CNN-PCA algorithm is applied for the generation of conditional 3D realizations, defined on $60times60times40$ grids, for three geological scenarios (binary and bimodal channelized systems, and a three-facies channel-levee-mud system). CNN-PCA realizations are shown to exhibit geological features that are visually consistent with reference models generated using object-based methods. Statistics of flow responses ($text{P}_{10}$, $text{P}_{50}$, $text{P}_{90}$ percentile results) for test sets of 3D CNN-PCA models are shown to be in consistent agreement with those from reference geomodels. Lastly, CNN-PCA is successfully applied for history matching with ESMDA for the bimodal channelized system." @default.
- W3043504355 created "2020-07-23" @default.
- W3043504355 creator A5002057296 @default.
- W3043504355 creator A5060920467 @default.
- W3043504355 date "2021-03-01" @default.
- W3043504355 modified "2023-10-01" @default.
- W3043504355 title "3D CNN-PCA: A deep-learning-based parameterization for complex geomodels" @default.
- W3043504355 cites W2000598248 @default.
- W3043504355 cites W2010762552 @default.
- W3043504355 cites W2018353504 @default.
- W3043504355 cites W2024330397 @default.
- W3043504355 cites W2056827945 @default.
- W3043504355 cites W2154121441 @default.
- W3043504355 cites W2298906243 @default.
- W3043504355 cites W2762902720 @default.
- W3043504355 cites W2916289860 @default.
- W3043504355 cites W2950337752 @default.
- W3043504355 cites W2963162215 @default.
- W3043504355 cites W2981785001 @default.
- W3043504355 cites W2999802832 @default.
- W3043504355 cites W3013677287 @default.
- W3043504355 cites W3014897790 @default.
- W3043504355 cites W3015570394 @default.
- W3043504355 cites W3016309349 @default.
- W3043504355 cites W3036800407 @default.
- W3043504355 cites W3104693082 @default.
- W3043504355 cites W3123551284 @default.
- W3043504355 doi "https://doi.org/10.1016/j.cageo.2020.104676" @default.
- W3043504355 hasPublicationYear "2021" @default.
- W3043504355 type Work @default.
- W3043504355 sameAs 3043504355 @default.
- W3043504355 citedByCount "27" @default.
- W3043504355 countsByYear W30435043552021 @default.
- W3043504355 countsByYear W30435043552022 @default.
- W3043504355 countsByYear W30435043552023 @default.
- W3043504355 crossrefType "journal-article" @default.
- W3043504355 hasAuthorship W3043504355A5002057296 @default.
- W3043504355 hasAuthorship W3043504355A5060920467 @default.
- W3043504355 hasBestOaLocation W30435043552 @default.
- W3043504355 hasConcept C108583219 @default.
- W3043504355 hasConcept C127313418 @default.
- W3043504355 hasConcept C151730666 @default.
- W3043504355 hasConcept C153180895 @default.
- W3043504355 hasConcept C154945302 @default.
- W3043504355 hasConcept C17744445 @default.
- W3043504355 hasConcept C199539241 @default.
- W3043504355 hasConcept C27438332 @default.
- W3043504355 hasConcept C2776359362 @default.
- W3043504355 hasConcept C2779343474 @default.
- W3043504355 hasConcept C41008148 @default.
- W3043504355 hasConcept C51889082 @default.
- W3043504355 hasConcept C76155785 @default.
- W3043504355 hasConcept C81363708 @default.
- W3043504355 hasConcept C94625758 @default.
- W3043504355 hasConceptScore W3043504355C108583219 @default.
- W3043504355 hasConceptScore W3043504355C127313418 @default.
- W3043504355 hasConceptScore W3043504355C151730666 @default.
- W3043504355 hasConceptScore W3043504355C153180895 @default.
- W3043504355 hasConceptScore W3043504355C154945302 @default.
- W3043504355 hasConceptScore W3043504355C17744445 @default.
- W3043504355 hasConceptScore W3043504355C199539241 @default.
- W3043504355 hasConceptScore W3043504355C27438332 @default.
- W3043504355 hasConceptScore W3043504355C2776359362 @default.
- W3043504355 hasConceptScore W3043504355C2779343474 @default.
- W3043504355 hasConceptScore W3043504355C41008148 @default.
- W3043504355 hasConceptScore W3043504355C51889082 @default.
- W3043504355 hasConceptScore W3043504355C76155785 @default.
- W3043504355 hasConceptScore W3043504355C81363708 @default.
- W3043504355 hasConceptScore W3043504355C94625758 @default.
- W3043504355 hasLocation W30435043551 @default.
- W3043504355 hasLocation W30435043552 @default.
- W3043504355 hasOpenAccess W3043504355 @default.
- W3043504355 hasPrimaryLocation W30435043551 @default.
- W3043504355 hasRelatedWork W2731899572 @default.
- W3043504355 hasRelatedWork W2732542196 @default.
- W3043504355 hasRelatedWork W2738221750 @default.
- W3043504355 hasRelatedWork W2766146978 @default.
- W3043504355 hasRelatedWork W3133861977 @default.
- W3043504355 hasRelatedWork W3156786002 @default.
- W3043504355 hasRelatedWork W4200173597 @default.
- W3043504355 hasRelatedWork W4312417841 @default.
- W3043504355 hasRelatedWork W4321369474 @default.
- W3043504355 hasRelatedWork W564581980 @default.
- W3043504355 hasVolume "148" @default.
- W3043504355 isParatext "false" @default.
- W3043504355 isRetracted "false" @default.
- W3043504355 magId "3043504355" @default.
- W3043504355 workType "article" @default.