Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377970019> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4377970019 abstract "Abstract Parametrization is widely used to improve the solution of ill-posed subsurface flow model calibration problems. Traditional low-dimensional parameterization methods consist of spatial and transform-domain methods with well-established mathematical properties that are mostly amenable to interpretation. More recent deep learning-based parametrization approaches exhibit strong performance in representing complex geological patterns but lack interpretability, making them less suitable for systematic updates based on expert knowledge. We present a disentangled parameterization approach with variational autoencoder (VAE) architecture to enable improved representation of complex spatial patterns and provide some degree of interpretability by allowing certain spatial features and attributes of a property map to be controlled by a single latent variable (generative factor), while remaining relatively invariant to changes in other latent factors. The existence of disentangled latent variables brings extra controllability to incorporate expert knowledge in making updates to the model. We explore two different approaches to achieve disentangled parameterization. In the first approach, we use β-VAE to learn disentangled factors in unsupervised learning manner, while in the second approach we apply the conditional VAE to represent discrete disentangled factors through supervised learning. By encoding the geologic scenarios into discrete latent codes, the parameterization enables automated scenario selection during inverse modeling and assisted updates on the spatial maps by experts. We present preliminary results using a single-phase pumping test example to show how model calibration can benefit from the proposed disentangled parameterization." @default.
- W4377970019 created "2023-05-25" @default.
- W4377970019 creator A5003736943 @default.
- W4377970019 creator A5009143452 @default.
- W4377970019 date "2023-03-21" @default.
- W4377970019 modified "2023-10-17" @default.
- W4377970019 title "Deep Learning-Based Disentangled Parametrization for Model Calibration Under Multiple Geologic Scenarios" @default.
- W4377970019 cites W1992548144 @default.
- W4377970019 cites W2005490094 @default.
- W4377970019 cites W2010762552 @default.
- W4377970019 cites W2011181254 @default.
- W4377970019 cites W2018302015 @default.
- W4377970019 cites W2027461913 @default.
- W4377970019 cites W2031614119 @default.
- W4377970019 cites W2078327207 @default.
- W4377970019 cites W2122538988 @default.
- W4377970019 cites W2126777570 @default.
- W4377970019 cites W2163922914 @default.
- W4377970019 cites W2496836423 @default.
- W4377970019 cites W2762902720 @default.
- W4377970019 cites W2905919278 @default.
- W4377970019 cites W2950337752 @default.
- W4377970019 cites W3080352642 @default.
- W4377970019 cites W3096831136 @default.
- W4377970019 cites W3103145119 @default.
- W4377970019 cites W3168360148 @default.
- W4377970019 cites W3203441253 @default.
- W4377970019 cites W3207102426 @default.
- W4377970019 cites W4252917338 @default.
- W4377970019 doi "https://doi.org/10.2118/212177-ms" @default.
- W4377970019 hasPublicationYear "2023" @default.
- W4377970019 type Work @default.
- W4377970019 citedByCount "0" @default.
- W4377970019 crossrefType "proceedings-article" @default.
- W4377970019 hasAuthorship W4377970019A5003736943 @default.
- W4377970019 hasAuthorship W4377970019A5009143452 @default.
- W4377970019 hasConcept C101738243 @default.
- W4377970019 hasConcept C108583219 @default.
- W4377970019 hasConcept C119857082 @default.
- W4377970019 hasConcept C121332964 @default.
- W4377970019 hasConcept C124101348 @default.
- W4377970019 hasConcept C154945302 @default.
- W4377970019 hasConcept C17744445 @default.
- W4377970019 hasConcept C199539241 @default.
- W4377970019 hasConcept C202887219 @default.
- W4377970019 hasConcept C2776359362 @default.
- W4377970019 hasConcept C2781067378 @default.
- W4377970019 hasConcept C41008148 @default.
- W4377970019 hasConcept C51167844 @default.
- W4377970019 hasConcept C62520636 @default.
- W4377970019 hasConcept C74902906 @default.
- W4377970019 hasConcept C94625758 @default.
- W4377970019 hasConceptScore W4377970019C101738243 @default.
- W4377970019 hasConceptScore W4377970019C108583219 @default.
- W4377970019 hasConceptScore W4377970019C119857082 @default.
- W4377970019 hasConceptScore W4377970019C121332964 @default.
- W4377970019 hasConceptScore W4377970019C124101348 @default.
- W4377970019 hasConceptScore W4377970019C154945302 @default.
- W4377970019 hasConceptScore W4377970019C17744445 @default.
- W4377970019 hasConceptScore W4377970019C199539241 @default.
- W4377970019 hasConceptScore W4377970019C202887219 @default.
- W4377970019 hasConceptScore W4377970019C2776359362 @default.
- W4377970019 hasConceptScore W4377970019C2781067378 @default.
- W4377970019 hasConceptScore W4377970019C41008148 @default.
- W4377970019 hasConceptScore W4377970019C51167844 @default.
- W4377970019 hasConceptScore W4377970019C62520636 @default.
- W4377970019 hasConceptScore W4377970019C74902906 @default.
- W4377970019 hasConceptScore W4377970019C94625758 @default.
- W4377970019 hasLocation W43779700191 @default.
- W4377970019 hasOpenAccess W4377970019 @default.
- W4377970019 hasPrimaryLocation W43779700191 @default.
- W4377970019 hasRelatedWork W2605281151 @default.
- W4377970019 hasRelatedWork W2955953864 @default.
- W4377970019 hasRelatedWork W2973572658 @default.
- W4377970019 hasRelatedWork W3006943036 @default.
- W4377970019 hasRelatedWork W3044458868 @default.
- W4377970019 hasRelatedWork W3081397225 @default.
- W4377970019 hasRelatedWork W3191046242 @default.
- W4377970019 hasRelatedWork W4213225422 @default.
- W4377970019 hasRelatedWork W4294031299 @default.
- W4377970019 hasRelatedWork W4299487748 @default.
- W4377970019 isParatext "false" @default.
- W4377970019 isRetracted "false" @default.
- W4377970019 workType "article" @default.