Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897069247> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2897069247 abstract "In carbon capture and sequestration (also known as carbon capture andstorage, or CCS), developing effective monitoring methods is needed to detectand respond to CO2 leakage. CO2 leakage detection methods rely on geophysicalobservations and monitoring sensor network. However, traditional methodsusually require development of site-specific physical models and expertinterpretation, and the effectiveness of these methods can be limited to thedifferent application locations, operational scenarios, and conditions. In thispaper, we developed a novel data-driven leakage detection method based ondensely connected convolutional neural networks. Our method is an end-to-enddetection approach, that differs from conventional leakage monitoring methodsby directly learning a mapping relationship between seismic data and the CO2leakage mass. To account for the spatial and temporal characteristics ofseismic data, our novel networks architecture combines 1D and 2D convolutionalneural networks. To overcome the computational expense of solving optimizationproblems, we apply a densely-connecting strategy in our network architecturethat reduces the number of network parameters. Based on the features generatedby our convolutional neural networks, we further incorporate a long short-termmemory network to utilize time-sequential information, which further improvesthe detection accuracy. Finally, we employ our detection method to syntheticseismic datasets generated based on flow simulations of a hypothetical CO2storage scenario with injection into a partially compartmentalized sandstonestorage reservoir. To evaluate method performance, we conducted multipleexperiments including a random leakage test, a sequential test, and arobustness test." @default.
- W2897069247 created "2018-10-26" @default.
- W2897069247 creator A5001857687 @default.
- W2897069247 creator A5005287327 @default.
- W2897069247 creator A5025218521 @default.
- W2897069247 creator A5033959506 @default.
- W2897069247 creator A5052676856 @default.
- W2897069247 creator A5080330902 @default.
- W2897069247 creator A5084040355 @default.
- W2897069247 date "2018-10-13" @default.
- W2897069247 modified "2023-09-24" @default.
- W2897069247 title "Spatial-Temporal Densely Connected CNN-LSTM Nets: An Application to CO2 Leakage Detection" @default.
- W2897069247 hasPublicationYear "2018" @default.
- W2897069247 type Work @default.
- W2897069247 sameAs 2897069247 @default.
- W2897069247 citedByCount "0" @default.
- W2897069247 crossrefType "posted-content" @default.
- W2897069247 hasAuthorship W2897069247A5001857687 @default.
- W2897069247 hasAuthorship W2897069247A5005287327 @default.
- W2897069247 hasAuthorship W2897069247A5025218521 @default.
- W2897069247 hasAuthorship W2897069247A5033959506 @default.
- W2897069247 hasAuthorship W2897069247A5052676856 @default.
- W2897069247 hasAuthorship W2897069247A5080330902 @default.
- W2897069247 hasAuthorship W2897069247A5084040355 @default.
- W2897069247 hasConcept C104317684 @default.
- W2897069247 hasConcept C124101348 @default.
- W2897069247 hasConcept C139719470 @default.
- W2897069247 hasConcept C153180895 @default.
- W2897069247 hasConcept C154945302 @default.
- W2897069247 hasConcept C162324750 @default.
- W2897069247 hasConcept C185592680 @default.
- W2897069247 hasConcept C2777042071 @default.
- W2897069247 hasConcept C41008148 @default.
- W2897069247 hasConcept C55493867 @default.
- W2897069247 hasConcept C63479239 @default.
- W2897069247 hasConcept C79403827 @default.
- W2897069247 hasConcept C81363708 @default.
- W2897069247 hasConceptScore W2897069247C104317684 @default.
- W2897069247 hasConceptScore W2897069247C124101348 @default.
- W2897069247 hasConceptScore W2897069247C139719470 @default.
- W2897069247 hasConceptScore W2897069247C153180895 @default.
- W2897069247 hasConceptScore W2897069247C154945302 @default.
- W2897069247 hasConceptScore W2897069247C162324750 @default.
- W2897069247 hasConceptScore W2897069247C185592680 @default.
- W2897069247 hasConceptScore W2897069247C2777042071 @default.
- W2897069247 hasConceptScore W2897069247C41008148 @default.
- W2897069247 hasConceptScore W2897069247C55493867 @default.
- W2897069247 hasConceptScore W2897069247C63479239 @default.
- W2897069247 hasConceptScore W2897069247C79403827 @default.
- W2897069247 hasConceptScore W2897069247C81363708 @default.
- W2897069247 hasLocation W28970692471 @default.
- W2897069247 hasOpenAccess W2897069247 @default.
- W2897069247 hasPrimaryLocation W28970692471 @default.
- W2897069247 hasRelatedWork W2153610999 @default.
- W2897069247 hasRelatedWork W2584007825 @default.
- W2897069247 hasRelatedWork W2805267115 @default.
- W2897069247 hasRelatedWork W2875840718 @default.
- W2897069247 hasRelatedWork W2892093300 @default.
- W2897069247 hasRelatedWork W2901173979 @default.
- W2897069247 hasRelatedWork W2903654288 @default.
- W2897069247 hasRelatedWork W2940786566 @default.
- W2897069247 hasRelatedWork W2963087201 @default.
- W2897069247 hasRelatedWork W2969534742 @default.
- W2897069247 hasRelatedWork W2969572277 @default.
- W2897069247 hasRelatedWork W3034504400 @default.
- W2897069247 hasRelatedWork W3092694705 @default.
- W2897069247 hasRelatedWork W3097458514 @default.
- W2897069247 hasRelatedWork W3099762966 @default.
- W2897069247 hasRelatedWork W3112309207 @default.
- W2897069247 hasRelatedWork W3115507218 @default.
- W2897069247 hasRelatedWork W3116371285 @default.
- W2897069247 hasRelatedWork W3118957360 @default.
- W2897069247 hasRelatedWork W3178046435 @default.
- W2897069247 isParatext "false" @default.
- W2897069247 isRetracted "false" @default.
- W2897069247 magId "2897069247" @default.
- W2897069247 workType "article" @default.