Matches in SemOpenAlex for { <https://semopenalex.org/work/W3123670553> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3123670553 endingPage "R317" @default.
- W3123670553 startingPage "R303" @default.
- W3123670553 abstract "The determination of subsurface elastic property models is crucial in quantitative seismic data processing and interpretation. This problem is commonly solved by deterministic physical methods, such as tomography or full-waveform inversion. However, these methods are entirely local and require accurate initial models. Deep learning represents a plausible class of methods for seismic inversion, which may avoid some of the issues of purely descent-based approaches. However, any generic deep learning network capable of relating each elastic property cell value to each sample in a seismic data set would require a very large number of degrees of freedom. Two approaches might be taken to train such a network: first, by invoking a massive and exhaustive training data set and, second, by working to reduce the degrees of freedom by enforcing physical constraints on the model-data relationship. The second approach is referred to as “physics-guiding.” Based on recent progress in wave theory-designed (i.e., physics-based) networks, we have developed a hybrid network design, involving deterministic, physics-based modeling and data-driven deep learning components. From an optimization standpoint, a data-driven model misfit (i.e., standard deep learning) and now a physics-guided data residual (i.e., a wave propagation network) are simultaneously minimized during the training of the network. An experiment is carried out to analyze the trade-off between two types of losses. Synthetic velocity building is used to examine the potential of hybrid training. Comparisons demonstrate that, given the same training data set, the hybrid-trained network outperforms the traditional fully data-driven network. In addition, we perform a comprehensive error analysis to quantitatively compare the fully data-driven and hybrid physics-guided approaches. The network is applied to the SEG salt model data, and the uncertainty is analyzed, to further examine the benefits of hybrid training." @default.
- W3123670553 created "2021-02-01" @default.
- W3123670553 creator A5004183775 @default.
- W3123670553 creator A5024863047 @default.
- W3123670553 creator A5033587288 @default.
- W3123670553 date "2021-03-19" @default.
- W3123670553 modified "2023-10-03" @default.
- W3123670553 title "Physics-guided deep learning for seismic inversion with hybrid training and uncertainty analysis" @default.
- W3123670553 cites W1901129140 @default.
- W3123670553 cites W1903029394 @default.
- W3123670553 cites W2009552164 @default.
- W3123670553 cites W2085807520 @default.
- W3123670553 cites W2100245965 @default.
- W3123670553 cites W2115637982 @default.
- W3123670553 cites W2133665775 @default.
- W3123670553 cites W2163688154 @default.
- W3123670553 cites W2242218935 @default.
- W3123670553 cites W2508457857 @default.
- W3123670553 cites W2592421213 @default.
- W3123670553 cites W2776585113 @default.
- W3123670553 cites W2798538010 @default.
- W3123670553 cites W2912052494 @default.
- W3123670553 cites W2923484039 @default.
- W3123670553 cites W2947704004 @default.
- W3123670553 cites W2955412401 @default.
- W3123670553 cites W2963008249 @default.
- W3123670553 cites W2963787510 @default.
- W3123670553 cites W2967127111 @default.
- W3123670553 cites W2967196803 @default.
- W3123670553 cites W2967236175 @default.
- W3123670553 cites W2968094316 @default.
- W3123670553 cites W2968844033 @default.
- W3123670553 cites W2969941231 @default.
- W3123670553 cites W2981504057 @default.
- W3123670553 cites W2983807332 @default.
- W3123670553 cites W2986812080 @default.
- W3123670553 cites W3032991056 @default.
- W3123670553 cites W3091722481 @default.
- W3123670553 doi "https://doi.org/10.1190/geo2020-0312.1" @default.
- W3123670553 hasPublicationYear "2021" @default.
- W3123670553 type Work @default.
- W3123670553 sameAs 3123670553 @default.
- W3123670553 citedByCount "60" @default.
- W3123670553 countsByYear W31236705532021 @default.
- W3123670553 countsByYear W31236705532022 @default.
- W3123670553 countsByYear W31236705532023 @default.
- W3123670553 crossrefType "journal-article" @default.
- W3123670553 hasAuthorship W3123670553A5004183775 @default.
- W3123670553 hasAuthorship W3123670553A5024863047 @default.
- W3123670553 hasAuthorship W3123670553A5033587288 @default.
- W3123670553 hasConcept C108583219 @default.
- W3123670553 hasConcept C11413529 @default.
- W3123670553 hasConcept C119857082 @default.
- W3123670553 hasConcept C127313418 @default.
- W3123670553 hasConcept C154945302 @default.
- W3123670553 hasConcept C155512373 @default.
- W3123670553 hasConcept C160920958 @default.
- W3123670553 hasConcept C165205528 @default.
- W3123670553 hasConcept C177264268 @default.
- W3123670553 hasConcept C1893757 @default.
- W3123670553 hasConcept C199360897 @default.
- W3123670553 hasConcept C41008148 @default.
- W3123670553 hasConcept C50644808 @default.
- W3123670553 hasConcept C77928131 @default.
- W3123670553 hasConceptScore W3123670553C108583219 @default.
- W3123670553 hasConceptScore W3123670553C11413529 @default.
- W3123670553 hasConceptScore W3123670553C119857082 @default.
- W3123670553 hasConceptScore W3123670553C127313418 @default.
- W3123670553 hasConceptScore W3123670553C154945302 @default.
- W3123670553 hasConceptScore W3123670553C155512373 @default.
- W3123670553 hasConceptScore W3123670553C160920958 @default.
- W3123670553 hasConceptScore W3123670553C165205528 @default.
- W3123670553 hasConceptScore W3123670553C177264268 @default.
- W3123670553 hasConceptScore W3123670553C1893757 @default.
- W3123670553 hasConceptScore W3123670553C199360897 @default.
- W3123670553 hasConceptScore W3123670553C41008148 @default.
- W3123670553 hasConceptScore W3123670553C50644808 @default.
- W3123670553 hasConceptScore W3123670553C77928131 @default.
- W3123670553 hasFunder F4320334593 @default.
- W3123670553 hasIssue "3" @default.
- W3123670553 hasLocation W31236705531 @default.
- W3123670553 hasOpenAccess W3123670553 @default.
- W3123670553 hasPrimaryLocation W31236705531 @default.
- W3123670553 hasRelatedWork W2922457425 @default.
- W3123670553 hasRelatedWork W3014300295 @default.
- W3123670553 hasRelatedWork W3164822677 @default.
- W3123670553 hasRelatedWork W3215138031 @default.
- W3123670553 hasRelatedWork W4223943233 @default.
- W3123670553 hasRelatedWork W4225161397 @default.
- W3123670553 hasRelatedWork W4250304930 @default.
- W3123670553 hasRelatedWork W4299487748 @default.
- W3123670553 hasRelatedWork W4309045103 @default.
- W3123670553 hasRelatedWork W4312200629 @default.
- W3123670553 hasVolume "86" @default.
- W3123670553 isParatext "false" @default.
- W3123670553 isRetracted "false" @default.
- W3123670553 magId "3123670553" @default.
- W3123670553 workType "article" @default.