Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090803408> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3090803408 abstract "Achieving desirable receiver sampling in ocean bottom acquisition is often not possible because of cost considerations. Assuming adequate source sampling is available, which is achievable by virtue of reciprocity and the use of modern randomized (simultaneous-source) marine acquisition technology, we are in a position to train convolutional neural networks (CNNs) to bring the receiver sampling to the same spatial grid as the dense source sampling. To accomplish this task, we form training pairs consisting of densely sampled data and artificially subsampled data using a reciprocity argument and the assumption that the source-site sampling is dense. While this approach has successfully been used on the recovery monochromatic frequency slices, its application in practice calls for wavefield reconstruction of time-domain data. Despite having the option to parallelize, the overall costs of this approach can become prohibitive if we decide to carry out the training and recovery independently for each frequency. Because different frequency slices share information, we propose the use the method of transfer training to make our approach computationally more efficient by warm starting the training with CNN weights obtained from a neighboring frequency slices. If the two neighboring frequency slices share information, we would expect the training to improve and converge faster. Our aim is to prove this principle by carrying a series of carefully selected experiments on a relatively large-scale five-dimensional data synthetic data volume associated with wide-azimuth 3D ocean bottom node acquisition. From these experiments, we observe that by transfer training we are able t significantly speedup in the training, specially at relatively higher frequencies where consecutive frequency slices are more correlated." @default.
- W3090803408 created "2020-10-08" @default.
- W3090803408 creator A5010780250 @default.
- W3090803408 creator A5036897639 @default.
- W3090803408 creator A5044553315 @default.
- W3090803408 date "2020-09-30" @default.
- W3090803408 modified "2023-10-18" @default.
- W3090803408 title "Transfer learning in large-scale ocean bottom seismic wavefield reconstruction" @default.
- W3090803408 cites W1822012234 @default.
- W3090803408 cites W2141953966 @default.
- W3090803408 cites W2165698076 @default.
- W3090803408 cites W2194493324 @default.
- W3090803408 cites W2194775991 @default.
- W3090803408 cites W2216762059 @default.
- W3090803408 cites W2331128040 @default.
- W3090803408 cites W2338019868 @default.
- W3090803408 cites W2891749414 @default.
- W3090803408 cites W2963073614 @default.
- W3090803408 cites W2963433607 @default.
- W3090803408 cites W2963600109 @default.
- W3090803408 cites W2966618135 @default.
- W3090803408 cites W2968967238 @default.
- W3090803408 cites W2969142131 @default.
- W3090803408 cites W2982303846 @default.
- W3090803408 doi "https://doi.org/10.1190/segam2020-3427882.1" @default.
- W3090803408 hasPublicationYear "2020" @default.
- W3090803408 type Work @default.
- W3090803408 sameAs 3090803408 @default.
- W3090803408 citedByCount "2" @default.
- W3090803408 countsByYear W30908034082022 @default.
- W3090803408 crossrefType "proceedings-article" @default.
- W3090803408 hasAuthorship W3090803408A5010780250 @default.
- W3090803408 hasAuthorship W3090803408A5036897639 @default.
- W3090803408 hasAuthorship W3090803408A5044553315 @default.
- W3090803408 hasBestOaLocation W30908034082 @default.
- W3090803408 hasConcept C106131492 @default.
- W3090803408 hasConcept C111919701 @default.
- W3090803408 hasConcept C11413529 @default.
- W3090803408 hasConcept C124101348 @default.
- W3090803408 hasConcept C127313418 @default.
- W3090803408 hasConcept C13280743 @default.
- W3090803408 hasConcept C140779682 @default.
- W3090803408 hasConcept C150899416 @default.
- W3090803408 hasConcept C154945302 @default.
- W3090803408 hasConcept C15744967 @default.
- W3090803408 hasConcept C159737794 @default.
- W3090803408 hasConcept C163985040 @default.
- W3090803408 hasConcept C169903001 @default.
- W3090803408 hasConcept C187691185 @default.
- W3090803408 hasConcept C19118579 @default.
- W3090803408 hasConcept C2524010 @default.
- W3090803408 hasConcept C31972630 @default.
- W3090803408 hasConcept C33923547 @default.
- W3090803408 hasConcept C41008148 @default.
- W3090803408 hasConcept C68339613 @default.
- W3090803408 hasConcept C77805123 @default.
- W3090803408 hasConcept C81363708 @default.
- W3090803408 hasConceptScore W3090803408C106131492 @default.
- W3090803408 hasConceptScore W3090803408C111919701 @default.
- W3090803408 hasConceptScore W3090803408C11413529 @default.
- W3090803408 hasConceptScore W3090803408C124101348 @default.
- W3090803408 hasConceptScore W3090803408C127313418 @default.
- W3090803408 hasConceptScore W3090803408C13280743 @default.
- W3090803408 hasConceptScore W3090803408C140779682 @default.
- W3090803408 hasConceptScore W3090803408C150899416 @default.
- W3090803408 hasConceptScore W3090803408C154945302 @default.
- W3090803408 hasConceptScore W3090803408C15744967 @default.
- W3090803408 hasConceptScore W3090803408C159737794 @default.
- W3090803408 hasConceptScore W3090803408C163985040 @default.
- W3090803408 hasConceptScore W3090803408C169903001 @default.
- W3090803408 hasConceptScore W3090803408C187691185 @default.
- W3090803408 hasConceptScore W3090803408C19118579 @default.
- W3090803408 hasConceptScore W3090803408C2524010 @default.
- W3090803408 hasConceptScore W3090803408C31972630 @default.
- W3090803408 hasConceptScore W3090803408C33923547 @default.
- W3090803408 hasConceptScore W3090803408C41008148 @default.
- W3090803408 hasConceptScore W3090803408C68339613 @default.
- W3090803408 hasConceptScore W3090803408C77805123 @default.
- W3090803408 hasConceptScore W3090803408C81363708 @default.
- W3090803408 hasLocation W30908034081 @default.
- W3090803408 hasLocation W30908034082 @default.
- W3090803408 hasOpenAccess W3090803408 @default.
- W3090803408 hasPrimaryLocation W30908034081 @default.
- W3090803408 hasRelatedWork W1968702681 @default.
- W3090803408 hasRelatedWork W1983565974 @default.
- W3090803408 hasRelatedWork W2025471448 @default.
- W3090803408 hasRelatedWork W2031573214 @default.
- W3090803408 hasRelatedWork W2033280630 @default.
- W3090803408 hasRelatedWork W2093994190 @default.
- W3090803408 hasRelatedWork W2152210047 @default.
- W3090803408 hasRelatedWork W2167517487 @default.
- W3090803408 hasRelatedWork W2371527909 @default.
- W3090803408 hasRelatedWork W4253374395 @default.
- W3090803408 isParatext "false" @default.
- W3090803408 isRetracted "false" @default.
- W3090803408 magId "3090803408" @default.
- W3090803408 workType "article" @default.