Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210291226> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4210291226 endingPage "SC40" @default.
- W4210291226 startingPage "SC31" @default.
- W4210291226 abstract "Several published solutions exist for the automatization of seismic facies labeling. We suggest an approach that applies tools from deep learning and semantic image segmentation, such as specific UNet-based neural network structure, total variation (TV) loss, pseudolabels, as well as domain-specific attributes and a novel image-warping augmentation technique. We use a patch-based training and prediction approach, and at the prediction stage, the facies labels for the test cube are collected with the patch overlap and with the averaging of the predictions. When applied to two open-source labeled seismic cubes, the algorithm demonstrates superior performance compared with the published results with regard to several metrics computed, such as accuracy, intersection-over-union, and F1 score. We compare the model predictions with and without the domain-specific augmentation and the pseudolabel approach with the metrics suggesting that the augmentation and the pseudolabels provide an increase in the model’s performance. Our method provides smoother labels due to the use of TV loss and pseudolabels, which is proved by the visual observation of the predictions of the final model in comparison with the baseline raw UNet model results." @default.
- W4210291226 created "2022-02-08" @default.
- W4210291226 creator A5033742122 @default.
- W4210291226 creator A5046830646 @default.
- W4210291226 date "2022-03-14" @default.
- W4210291226 modified "2023-09-29" @default.
- W4210291226 title "Deep learning for automated seismic facies classification" @default.
- W4210291226 cites W1745334888 @default.
- W4210291226 cites W1901129140 @default.
- W4210291226 cites W1973785137 @default.
- W4210291226 cites W2061680100 @default.
- W4210291226 cites W2516496171 @default.
- W4210291226 cites W2734349601 @default.
- W4210291226 cites W2807914764 @default.
- W4210291226 cites W2808760859 @default.
- W4210291226 cites W2889867094 @default.
- W4210291226 cites W2962914239 @default.
- W4210291226 cites W2963043051 @default.
- W4210291226 cites W2963794428 @default.
- W4210291226 cites W2963941635 @default.
- W4210291226 cites W2968138506 @default.
- W4210291226 cites W2968247551 @default.
- W4210291226 cites W2982640424 @default.
- W4210291226 cites W3005466525 @default.
- W4210291226 cites W3011644199 @default.
- W4210291226 cites W3033008664 @default.
- W4210291226 cites W3034785488 @default.
- W4210291226 cites W3106524252 @default.
- W4210291226 cites W3112055319 @default.
- W4210291226 cites W3135210147 @default.
- W4210291226 doi "https://doi.org/10.1190/int-2021-0140.1" @default.
- W4210291226 hasPublicationYear "2022" @default.
- W4210291226 type Work @default.
- W4210291226 citedByCount "3" @default.
- W4210291226 countsByYear W42102912262023 @default.
- W4210291226 crossrefType "journal-article" @default.
- W4210291226 hasAuthorship W4210291226A5033742122 @default.
- W4210291226 hasAuthorship W4210291226A5046830646 @default.
- W4210291226 hasConcept C108583219 @default.
- W4210291226 hasConcept C109007969 @default.
- W4210291226 hasConcept C114614502 @default.
- W4210291226 hasConcept C115961682 @default.
- W4210291226 hasConcept C127313418 @default.
- W4210291226 hasConcept C127413603 @default.
- W4210291226 hasConcept C146588470 @default.
- W4210291226 hasConcept C146978453 @default.
- W4210291226 hasConcept C151730666 @default.
- W4210291226 hasConcept C153180895 @default.
- W4210291226 hasConcept C154945302 @default.
- W4210291226 hasConcept C157202957 @default.
- W4210291226 hasConcept C33923547 @default.
- W4210291226 hasConcept C41008148 @default.
- W4210291226 hasConcept C50644808 @default.
- W4210291226 hasConcept C53051483 @default.
- W4210291226 hasConcept C64543145 @default.
- W4210291226 hasConcept C89600930 @default.
- W4210291226 hasConceptScore W4210291226C108583219 @default.
- W4210291226 hasConceptScore W4210291226C109007969 @default.
- W4210291226 hasConceptScore W4210291226C114614502 @default.
- W4210291226 hasConceptScore W4210291226C115961682 @default.
- W4210291226 hasConceptScore W4210291226C127313418 @default.
- W4210291226 hasConceptScore W4210291226C127413603 @default.
- W4210291226 hasConceptScore W4210291226C146588470 @default.
- W4210291226 hasConceptScore W4210291226C146978453 @default.
- W4210291226 hasConceptScore W4210291226C151730666 @default.
- W4210291226 hasConceptScore W4210291226C153180895 @default.
- W4210291226 hasConceptScore W4210291226C154945302 @default.
- W4210291226 hasConceptScore W4210291226C157202957 @default.
- W4210291226 hasConceptScore W4210291226C33923547 @default.
- W4210291226 hasConceptScore W4210291226C41008148 @default.
- W4210291226 hasConceptScore W4210291226C50644808 @default.
- W4210291226 hasConceptScore W4210291226C53051483 @default.
- W4210291226 hasConceptScore W4210291226C64543145 @default.
- W4210291226 hasConceptScore W4210291226C89600930 @default.
- W4210291226 hasIssue "2" @default.
- W4210291226 hasLocation W42102912261 @default.
- W4210291226 hasOpenAccess W4210291226 @default.
- W4210291226 hasPrimaryLocation W42102912261 @default.
- W4210291226 hasRelatedWork W2731899572 @default.
- W4210291226 hasRelatedWork W2738221750 @default.
- W4210291226 hasRelatedWork W2790662084 @default.
- W4210291226 hasRelatedWork W2954384599 @default.
- W4210291226 hasRelatedWork W2960184797 @default.
- W4210291226 hasRelatedWork W3012401223 @default.
- W4210291226 hasRelatedWork W3104734424 @default.
- W4210291226 hasRelatedWork W3209779739 @default.
- W4210291226 hasRelatedWork W4226289457 @default.
- W4210291226 hasRelatedWork W4285827401 @default.
- W4210291226 hasVolume "10" @default.
- W4210291226 isParatext "false" @default.
- W4210291226 isRetracted "false" @default.
- W4210291226 workType "article" @default.