Matches in SemOpenAlex for { <https://semopenalex.org/work/W2995504702> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2995504702 endingPage "3212" @default.
- W2995504702 startingPage "3202" @default.
- W2995504702 abstract "Bright spots, strong indicators of the existence of hydrocarbon accumulations, have been primarily used by geophysicists in oil and gas exploration. Recently, machine-learning algorithms, adopted to automate bright spot detection, have mainly relied on feature extraction and shallow classification workflows to achieve an 85.4% F1 score at best, on 2-D seismic data. Deep neural networks have proved their effectiveness in image classification applications, outperforming humans in some instances, but have not been applied to bright spot detection yet. However, their data-hungry nature poses a challenge in domains suffering from expensive data acquisition, such as seismic data analysis problems; they generally require millions of training samples before achieving good performance. In this article, we implement SeisNet, a convolutional neural network with a “butterfly” architecture that overcame the limited data challenge by implementing data augmentation and inductive transfer-learning techniques. Moreover, we adopt a novel formulation that allows us to detect bright spots and estimate their volume. Our approach was tested against different pretraining and transfer-learning methods and was shown to outperform other approaches in the literature by achieving a 95.6% F1 score on bright spot detection. Our model accurately predicted the volume of the bright spot with an average absolute error that is not more than 0.04% of the total volume of the seismic image. This article is an important step in establishing pretrained networks for other seismic applications such as earthquake prediction; our domain-specific pretrained network, proven to outperform state-of-the-art pretrained networks on bright spot detection, may be used to jump-start the training of deep models on other seismic problems." @default.
- W2995504702 created "2019-12-26" @default.
- W2995504702 creator A5005954815 @default.
- W2995504702 creator A5008382926 @default.
- W2995504702 creator A5058002550 @default.
- W2995504702 date "2020-05-01" @default.
- W2995504702 modified "2023-09-29" @default.
- W2995504702 title "A Deep Transfer Learning Framework for Seismic Data Analysis: A Case Study on Bright Spot Detection" @default.
- W2995504702 cites W1489507667 @default.
- W2995504702 cites W1905882502 @default.
- W2995504702 cites W1931639407 @default.
- W2995504702 cites W1969063328 @default.
- W2995504702 cites W2100897876 @default.
- W2995504702 cites W2163922914 @default.
- W2995504702 cites W2165698076 @default.
- W2995504702 cites W2194775991 @default.
- W2995504702 cites W2504830112 @default.
- W2995504702 cites W2510001968 @default.
- W2995504702 cites W2555042113 @default.
- W2995504702 cites W2592421213 @default.
- W2995504702 cites W2592517375 @default.
- W2995504702 cites W2608847424 @default.
- W2995504702 cites W2762410434 @default.
- W2995504702 cites W2767399675 @default.
- W2995504702 cites W2776585113 @default.
- W2995504702 cites W2783165089 @default.
- W2995504702 cites W2794436210 @default.
- W2995504702 cites W2889733417 @default.
- W2995504702 cites W2890715669 @default.
- W2995504702 cites W2891255706 @default.
- W2995504702 cites W2911424749 @default.
- W2995504702 cites W2912052494 @default.
- W2995504702 cites W2939587785 @default.
- W2995504702 cites W2947853264 @default.
- W2995504702 cites W2963108767 @default.
- W2995504702 cites W2963787510 @default.
- W2995504702 cites W2963941635 @default.
- W2995504702 cites W2967626886 @default.
- W2995504702 cites W4240485910 @default.
- W2995504702 cites W4241745324 @default.
- W2995504702 cites W4252593548 @default.
- W2995504702 doi "https://doi.org/10.1109/tgrs.2019.2950888" @default.
- W2995504702 hasPublicationYear "2020" @default.
- W2995504702 type Work @default.
- W2995504702 sameAs 2995504702 @default.
- W2995504702 citedByCount "23" @default.
- W2995504702 countsByYear W29955047022020 @default.
- W2995504702 countsByYear W29955047022021 @default.
- W2995504702 countsByYear W29955047022022 @default.
- W2995504702 countsByYear W29955047022023 @default.
- W2995504702 crossrefType "journal-article" @default.
- W2995504702 hasAuthorship W2995504702A5005954815 @default.
- W2995504702 hasAuthorship W2995504702A5008382926 @default.
- W2995504702 hasAuthorship W2995504702A5058002550 @default.
- W2995504702 hasConcept C127313418 @default.
- W2995504702 hasConcept C150899416 @default.
- W2995504702 hasConcept C154945302 @default.
- W2995504702 hasConcept C165205528 @default.
- W2995504702 hasConcept C41008148 @default.
- W2995504702 hasConcept C62649853 @default.
- W2995504702 hasConceptScore W2995504702C127313418 @default.
- W2995504702 hasConceptScore W2995504702C150899416 @default.
- W2995504702 hasConceptScore W2995504702C154945302 @default.
- W2995504702 hasConceptScore W2995504702C165205528 @default.
- W2995504702 hasConceptScore W2995504702C41008148 @default.
- W2995504702 hasConceptScore W2995504702C62649853 @default.
- W2995504702 hasFunder F4320309999 @default.
- W2995504702 hasFunder F4320332723 @default.
- W2995504702 hasIssue "5" @default.
- W2995504702 hasLocation W29955047021 @default.
- W2995504702 hasOpenAccess W2995504702 @default.
- W2995504702 hasPrimaryLocation W29955047021 @default.
- W2995504702 hasRelatedWork W1968702681 @default.
- W2995504702 hasRelatedWork W1969245073 @default.
- W2995504702 hasRelatedWork W2031573214 @default.
- W2995504702 hasRelatedWork W2092739438 @default.
- W2995504702 hasRelatedWork W2371527909 @default.
- W2995504702 hasRelatedWork W2772196783 @default.
- W2995504702 hasRelatedWork W3016255354 @default.
- W2995504702 hasRelatedWork W3036915269 @default.
- W2995504702 hasRelatedWork W3109652668 @default.
- W2995504702 hasRelatedWork W4220883378 @default.
- W2995504702 hasVolume "58" @default.
- W2995504702 isParatext "false" @default.
- W2995504702 isRetracted "false" @default.
- W2995504702 magId "2995504702" @default.
- W2995504702 workType "article" @default.