FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080352642> ?p ?o ?g. }

• W3080352642 endingPage "104762" @default.
• W3080352642 startingPage "104762" @default.
• W3080352642 abstract "When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological setting) of the subsurface. In such case, inversion may be formulated in a latent space where a low-dimensional parameterization of the patterns is defined and where Markov chain Monte Carlo or gradient-based methods may be applied. However, the generative mapping between the latent and the original (pixel) representations is usually highly nonlinear which may cause some difficulties for inversion, especially for gradient-based methods. In this contribution we review the conceptual framework of inversion with DGMs and propose that this nonlinearity is caused mainly by changes in topology and curvature induced by the generative function. As a result, we identify a conflict between two goals: the accuracy of the generated patterns and the feasibility of gradient-based inversion. In addition, we show how some of the training parameters of a variational autoencoder, which is a particular instance of a DGM, may be chosen so that a tradeoff between these two goals is achieved and acceptable inversion results are obtained with a stochastic gradient-descent scheme. A series of test cases using synthetic models with channel patterns of different complexity and cross-borehole traveltime tomographic data involving both a linear and a nonlinear forward operator show that the proposed method provides useful results and performs better compared to previous approaches using DGMs with gradient-based inversion." @default.
• W3080352642 created "2020-09-01" @default.
• W3080352642 creator A5025611150 @default.
• W3080352642 creator A5040329303 @default.
• W3080352642 creator A5042170410 @default.
• W3080352642 creator A5061454272 @default.
• W3080352642 date "2021-07-01" @default.
• W3080352642 modified "2023-10-17" @default.
• W3080352642 title "Deep generative models in inversion: The impact of the generator's nonlinearity and development of a new approach based on a variational autoencoder" @default.
• W3080352642 cites W1499512010 @default.
• W3080352642 cites W1537810918 @default.
• W3080352642 cites W1821143250 @default.
• W3080352642 cites W2010625929 @default.
• W3080352642 cites W2025756504 @default.
• W3080352642 cites W2029177589 @default.
• W3080352642 cites W2064321848 @default.
• W3080352642 cites W2079855895 @default.
• W3080352642 cites W2083600532 @default.
• W3080352642 cites W2123023966 @default.
• W3080352642 cites W2161336914 @default.
• W3080352642 cites W2164700406 @default.
• W3080352642 cites W2166954778 @default.
• W3080352642 cites W2328408066 @default.
• W3080352642 cites W2742540029 @default.
• W3080352642 cites W2762902720 @default.
• W3080352642 cites W2783089773 @default.
• W3080352642 cites W2896048271 @default.
• W3080352642 cites W2906141267 @default.
• W3080352642 cites W2950337752 @default.
• W3080352642 cites W2963693826 @default.
• W3080352642 cites W2999802832 @default.
• W3080352642 cites W3104223502 @default.
• W3080352642 cites W3123551284 @default.
• W3080352642 doi "https://doi.org/10.1016/j.cageo.2021.104762" @default.
• W3080352642 hasPublicationYear "2021" @default.
• W3080352642 type Work @default.
• W3080352642 sameAs 3080352642 @default.
• W3080352642 citedByCount "34" @default.
• W3080352642 countsByYear W30803526422021 @default.
• W3080352642 countsByYear W30803526422022 @default.
• W3080352642 countsByYear W30803526422023 @default.
• W3080352642 crossrefType "journal-article" @default.
• W3080352642 hasAuthorship W3080352642A5025611150 @default.
• W3080352642 hasAuthorship W3080352642A5040329303 @default.
• W3080352642 hasAuthorship W3080352642A5042170410 @default.
• W3080352642 hasAuthorship W3080352642A5061454272 @default.
• W3080352642 hasBestOaLocation W30803526422 @default.
• W3080352642 hasConcept C101738243 @default.
• W3080352642 hasConcept C108583219 @default.
• W3080352642 hasConcept C109007969 @default.
• W3080352642 hasConcept C11413529 @default.
• W3080352642 hasConcept C121332964 @default.
• W3080352642 hasConcept C127313418 @default.
• W3080352642 hasConcept C151730666 @default.
• W3080352642 hasConcept C154945302 @default.
• W3080352642 hasConcept C158622935 @default.
• W3080352642 hasConcept C1893757 @default.
• W3080352642 hasConcept C195065555 @default.
• W3080352642 hasConcept C2524010 @default.
• W3080352642 hasConcept C28826006 @default.
• W3080352642 hasConcept C33923547 @default.
• W3080352642 hasConcept C41008148 @default.
• W3080352642 hasConcept C41608201 @default.
• W3080352642 hasConcept C62520636 @default.
• W3080352642 hasConcept C8058405 @default.
• W3080352642 hasConceptScore W3080352642C101738243 @default.
• W3080352642 hasConceptScore W3080352642C108583219 @default.
• W3080352642 hasConceptScore W3080352642C109007969 @default.
• W3080352642 hasConceptScore W3080352642C11413529 @default.
• W3080352642 hasConceptScore W3080352642C121332964 @default.
• W3080352642 hasConceptScore W3080352642C127313418 @default.
• W3080352642 hasConceptScore W3080352642C151730666 @default.
• W3080352642 hasConceptScore W3080352642C154945302 @default.
• W3080352642 hasConceptScore W3080352642C158622935 @default.
• W3080352642 hasConceptScore W3080352642C1893757 @default.
• W3080352642 hasConceptScore W3080352642C195065555 @default.
• W3080352642 hasConceptScore W3080352642C2524010 @default.
• W3080352642 hasConceptScore W3080352642C28826006 @default.
• W3080352642 hasConceptScore W3080352642C33923547 @default.
• W3080352642 hasConceptScore W3080352642C41008148 @default.
• W3080352642 hasConceptScore W3080352642C41608201 @default.
• W3080352642 hasConceptScore W3080352642C62520636 @default.
• W3080352642 hasConceptScore W3080352642C8058405 @default.
• W3080352642 hasFunder F4320320300 @default.
• W3080352642 hasLocation W30803526421 @default.
• W3080352642 hasLocation W30803526422 @default.
• W3080352642 hasLocation W30803526423 @default.
• W3080352642 hasOpenAccess W3080352642 @default.
• W3080352642 hasPrimaryLocation W30803526421 @default.
• W3080352642 hasRelatedWork W2159052453 @default.
• W3080352642 hasRelatedWork W2566616303 @default.
• W3080352642 hasRelatedWork W2669956259 @default.
• W3080352642 hasRelatedWork W2734887215 @default.
• W3080352642 hasRelatedWork W2752972570 @default.
• W3080352642 hasRelatedWork W3013693939 @default.
• W3080352642 hasRelatedWork W3131327266 @default.
• W3080352642 hasRelatedWork W4249005693 @default.
• W3080352642 hasRelatedWork W4297051394 @default.

• next