Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045141> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4288045141 endingPage "104763" @default.
- W4288045141 startingPage "104763" @default.
- W4288045141 abstract "Full-waveform inversion (FWI) is a powerful technology for determining geophysical properties, nevertheless, with high computational cost and difficulty in convergence. Motivated by the powerful tools available in modern deep learning system to deal with complex non-linear inverse problems, we implement the FWI workflow with deep neural networks and propose the use of two different neural networks with adversarial losses to provide fast and accurate solutions. Specifically, a deep neural network is used to generate simulated seismic data based on the finite-difference method, and another fully connected neural network is used to fit the Wasserstein distance between simulated and observed seismic data. The Wasserstein distance and the L2 metric together form an adversarial loss function. The parallel-layer model and the SEAM model are used to verify the benefits of the proposed method and its performance in the face of seismic data lack low-frequency components and noise interference. Numerical experiments demonstrate that, compared with other algorithms, the adaptive gradient (Adagrad) algorithm performs best. In addition, the Adagrad algorithm with adversarial losses has faster convergence speed and more inverting details than with L2 losses. The proposed method provides reliable inversion results, even when seismic data without low-frequency components. Moreover, the adversarial losses are less sensitive to noise, although still difficult to converge." @default.
- W4288045141 created "2022-07-27" @default.
- W4288045141 creator A5003426360 @default.
- W4288045141 creator A5055128339 @default.
- W4288045141 creator A5064660687 @default.
- W4288045141 creator A5072240312 @default.
- W4288045141 creator A5082506668 @default.
- W4288045141 date "2022-10-01" @default.
- W4288045141 modified "2023-10-16" @default.
- W4288045141 title "Full-waveform inversion with adversarial losses via deep learning" @default.
- W4288045141 cites W2053376610 @default.
- W4288045141 cites W2100245965 @default.
- W4288045141 cites W2100717205 @default.
- W4288045141 cites W2345010043 @default.
- W4288045141 cites W2765811365 @default.
- W4288045141 cites W2776585113 @default.
- W4288045141 cites W2794622599 @default.
- W4288045141 cites W2894410771 @default.
- W4288045141 cites W2903747695 @default.
- W4288045141 cites W2912052494 @default.
- W4288045141 cites W2958537367 @default.
- W4288045141 cites W2963294122 @default.
- W4288045141 cites W2983807332 @default.
- W4288045141 cites W3011644199 @default.
- W4288045141 cites W3091837928 @default.
- W4288045141 cites W3111550989 @default.
- W4288045141 cites W3135339134 @default.
- W4288045141 doi "https://doi.org/10.1016/j.jappgeo.2022.104763" @default.
- W4288045141 hasPublicationYear "2022" @default.
- W4288045141 type Work @default.
- W4288045141 citedByCount "1" @default.
- W4288045141 countsByYear W42880451412023 @default.
- W4288045141 crossrefType "journal-article" @default.
- W4288045141 hasAuthorship W4288045141A5003426360 @default.
- W4288045141 hasAuthorship W4288045141A5055128339 @default.
- W4288045141 hasAuthorship W4288045141A5064660687 @default.
- W4288045141 hasAuthorship W4288045141A5072240312 @default.
- W4288045141 hasAuthorship W4288045141A5082506668 @default.
- W4288045141 hasConcept C108583219 @default.
- W4288045141 hasConcept C11413529 @default.
- W4288045141 hasConcept C126255220 @default.
- W4288045141 hasConcept C127313418 @default.
- W4288045141 hasConcept C134306372 @default.
- W4288045141 hasConcept C135252773 @default.
- W4288045141 hasConcept C154945302 @default.
- W4288045141 hasConcept C162324750 @default.
- W4288045141 hasConcept C165205528 @default.
- W4288045141 hasConcept C1893757 @default.
- W4288045141 hasConcept C2777303404 @default.
- W4288045141 hasConcept C2984842247 @default.
- W4288045141 hasConcept C33923547 @default.
- W4288045141 hasConcept C37736160 @default.
- W4288045141 hasConcept C41008148 @default.
- W4288045141 hasConcept C50522688 @default.
- W4288045141 hasConcept C50644808 @default.
- W4288045141 hasConcept C77928131 @default.
- W4288045141 hasConceptScore W4288045141C108583219 @default.
- W4288045141 hasConceptScore W4288045141C11413529 @default.
- W4288045141 hasConceptScore W4288045141C126255220 @default.
- W4288045141 hasConceptScore W4288045141C127313418 @default.
- W4288045141 hasConceptScore W4288045141C134306372 @default.
- W4288045141 hasConceptScore W4288045141C135252773 @default.
- W4288045141 hasConceptScore W4288045141C154945302 @default.
- W4288045141 hasConceptScore W4288045141C162324750 @default.
- W4288045141 hasConceptScore W4288045141C165205528 @default.
- W4288045141 hasConceptScore W4288045141C1893757 @default.
- W4288045141 hasConceptScore W4288045141C2777303404 @default.
- W4288045141 hasConceptScore W4288045141C2984842247 @default.
- W4288045141 hasConceptScore W4288045141C33923547 @default.
- W4288045141 hasConceptScore W4288045141C37736160 @default.
- W4288045141 hasConceptScore W4288045141C41008148 @default.
- W4288045141 hasConceptScore W4288045141C50522688 @default.
- W4288045141 hasConceptScore W4288045141C50644808 @default.
- W4288045141 hasConceptScore W4288045141C77928131 @default.
- W4288045141 hasFunder F4320321001 @default.
- W4288045141 hasLocation W42880451411 @default.
- W4288045141 hasOpenAccess W4288045141 @default.
- W4288045141 hasPrimaryLocation W42880451411 @default.
- W4288045141 hasRelatedWork W2777449390 @default.
- W4288045141 hasRelatedWork W2782217514 @default.
- W4288045141 hasRelatedWork W2903917280 @default.
- W4288045141 hasRelatedWork W2962700793 @default.
- W4288045141 hasRelatedWork W3033907886 @default.
- W4288045141 hasRelatedWork W3112589555 @default.
- W4288045141 hasRelatedWork W3193857078 @default.
- W4288045141 hasRelatedWork W4225493432 @default.
- W4288045141 hasRelatedWork W4291754871 @default.
- W4288045141 hasRelatedWork W4293054861 @default.
- W4288045141 hasVolume "205" @default.
- W4288045141 isParatext "false" @default.
- W4288045141 isRetracted "false" @default.
- W4288045141 workType "article" @default.