Application of conditional generative model for sonic log estimation considering measurement uncertainty
Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS da...
Ausführliche Beschreibung
Autor*in: |
Jeong, Jina [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2021transfer abstract |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
Enthalten in: Iterated Gilbert mosaics - Baccelli, Francois ELSEVIER, 2019, Amsterdam [u.a.] |
---|---|
Übergeordnetes Werk: |
volume:196 ; year:2021 ; pages:0 |
Links: |
---|
DOI / URN: |
10.1016/j.petrol.2020.108028 |
---|
Katalog-ID: |
ELV052479749 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | ELV052479749 | ||
003 | DE-627 | ||
005 | 20230626033337.0 | ||
007 | cr uuu---uuuuu | ||
008 | 210910s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.petrol.2020.108028 |2 doi | |
028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica |
035 | |a (DE-627)ELV052479749 | ||
035 | |a (ELSEVIER)S0920-4105(20)31083-4 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 510 |q VZ |
084 | |a 31.70 |2 bkl | ||
100 | 1 | |a Jeong, Jina |e verfasserin |4 aut | |
245 | 1 | 0 | |a Application of conditional generative model for sonic log estimation considering measurement uncertainty |
264 | 1 | |c 2021transfer abstract | |
336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
337 | |a nicht spezifiziert |b z |2 rdamedia | ||
338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
520 | |a Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. | ||
520 | |a Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. | ||
650 | 7 | |a Well-log estimation |2 Elsevier | |
650 | 7 | |a Conditional variational autoencoder |2 Elsevier | |
650 | 7 | |a Sensitivity analysis |2 Elsevier | |
650 | 7 | |a Bi-direction LSTM (Bi-LSTM) |2 Elsevier | |
650 | 7 | |a Long short-term memory (LSTM) |2 Elsevier | |
650 | 7 | |a Probabilistic estimation |2 Elsevier | |
700 | 1 | |a Park, Eungyu |4 oth | |
700 | 1 | |a Emelyanova, Irina |4 oth | |
700 | 1 | |a Pervukhina, Marina |4 oth | |
700 | 1 | |a Esteban, Lionel |4 oth | |
700 | 1 | |a Yun, Seong-Taek |4 oth | |
773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Baccelli, Francois ELSEVIER |t Iterated Gilbert mosaics |d 2019 |g Amsterdam [u.a.] |w (DE-627)ELV008094314 |
773 | 1 | 8 | |g volume:196 |g year:2021 |g pages:0 |
856 | 4 | 0 | |u https://doi.org/10.1016/j.petrol.2020.108028 |3 Volltext |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SYSFLAG_U | ||
912 | |a SSG-OPC-MAT | ||
936 | b | k | |a 31.70 |j Wahrscheinlichkeitsrechnung |q VZ |
951 | |a AR | ||
952 | |d 196 |j 2021 |h 0 |
author_variant |
j j jj |
---|---|
matchkey_str |
jeongjinaparkeungyuemelyanovairinapervuk:2021----:plctoocniinleeaieoefroilgsiainosdr |
hierarchy_sort_str |
2021transfer abstract |
bklnumber |
31.70 |
publishDate |
2021 |
allfields |
10.1016/j.petrol.2020.108028 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica (DE-627)ELV052479749 (ELSEVIER)S0920-4105(20)31083-4 DE-627 ger DE-627 rakwb eng 510 VZ 31.70 bkl Jeong, Jina verfasserin aut Application of conditional generative model for sonic log estimation considering measurement uncertainty 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation Elsevier Park, Eungyu oth Emelyanova, Irina oth Pervukhina, Marina oth Esteban, Lionel oth Yun, Seong-Taek oth Enthalten in Elsevier Science Baccelli, Francois ELSEVIER Iterated Gilbert mosaics 2019 Amsterdam [u.a.] (DE-627)ELV008094314 volume:196 year:2021 pages:0 https://doi.org/10.1016/j.petrol.2020.108028 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-MAT 31.70 Wahrscheinlichkeitsrechnung VZ AR 196 2021 0 |
spelling |
10.1016/j.petrol.2020.108028 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica (DE-627)ELV052479749 (ELSEVIER)S0920-4105(20)31083-4 DE-627 ger DE-627 rakwb eng 510 VZ 31.70 bkl Jeong, Jina verfasserin aut Application of conditional generative model for sonic log estimation considering measurement uncertainty 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation Elsevier Park, Eungyu oth Emelyanova, Irina oth Pervukhina, Marina oth Esteban, Lionel oth Yun, Seong-Taek oth Enthalten in Elsevier Science Baccelli, Francois ELSEVIER Iterated Gilbert mosaics 2019 Amsterdam [u.a.] (DE-627)ELV008094314 volume:196 year:2021 pages:0 https://doi.org/10.1016/j.petrol.2020.108028 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-MAT 31.70 Wahrscheinlichkeitsrechnung VZ AR 196 2021 0 |
allfields_unstemmed |
10.1016/j.petrol.2020.108028 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica (DE-627)ELV052479749 (ELSEVIER)S0920-4105(20)31083-4 DE-627 ger DE-627 rakwb eng 510 VZ 31.70 bkl Jeong, Jina verfasserin aut Application of conditional generative model for sonic log estimation considering measurement uncertainty 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation Elsevier Park, Eungyu oth Emelyanova, Irina oth Pervukhina, Marina oth Esteban, Lionel oth Yun, Seong-Taek oth Enthalten in Elsevier Science Baccelli, Francois ELSEVIER Iterated Gilbert mosaics 2019 Amsterdam [u.a.] (DE-627)ELV008094314 volume:196 year:2021 pages:0 https://doi.org/10.1016/j.petrol.2020.108028 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-MAT 31.70 Wahrscheinlichkeitsrechnung VZ AR 196 2021 0 |
allfieldsGer |
10.1016/j.petrol.2020.108028 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica (DE-627)ELV052479749 (ELSEVIER)S0920-4105(20)31083-4 DE-627 ger DE-627 rakwb eng 510 VZ 31.70 bkl Jeong, Jina verfasserin aut Application of conditional generative model for sonic log estimation considering measurement uncertainty 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation Elsevier Park, Eungyu oth Emelyanova, Irina oth Pervukhina, Marina oth Esteban, Lionel oth Yun, Seong-Taek oth Enthalten in Elsevier Science Baccelli, Francois ELSEVIER Iterated Gilbert mosaics 2019 Amsterdam [u.a.] (DE-627)ELV008094314 volume:196 year:2021 pages:0 https://doi.org/10.1016/j.petrol.2020.108028 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-MAT 31.70 Wahrscheinlichkeitsrechnung VZ AR 196 2021 0 |
allfieldsSound |
10.1016/j.petrol.2020.108028 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica (DE-627)ELV052479749 (ELSEVIER)S0920-4105(20)31083-4 DE-627 ger DE-627 rakwb eng 510 VZ 31.70 bkl Jeong, Jina verfasserin aut Application of conditional generative model for sonic log estimation considering measurement uncertainty 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation Elsevier Park, Eungyu oth Emelyanova, Irina oth Pervukhina, Marina oth Esteban, Lionel oth Yun, Seong-Taek oth Enthalten in Elsevier Science Baccelli, Francois ELSEVIER Iterated Gilbert mosaics 2019 Amsterdam [u.a.] (DE-627)ELV008094314 volume:196 year:2021 pages:0 https://doi.org/10.1016/j.petrol.2020.108028 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-MAT 31.70 Wahrscheinlichkeitsrechnung VZ AR 196 2021 0 |
language |
English |
source |
Enthalten in Iterated Gilbert mosaics Amsterdam [u.a.] volume:196 year:2021 pages:0 |
sourceStr |
Enthalten in Iterated Gilbert mosaics Amsterdam [u.a.] volume:196 year:2021 pages:0 |
format_phy_str_mv |
Article |
bklname |
Wahrscheinlichkeitsrechnung |
institution |
findex.gbv.de |
topic_facet |
Well-log estimation Conditional variational autoencoder Sensitivity analysis Bi-direction LSTM (Bi-LSTM) Long short-term memory (LSTM) Probabilistic estimation |
dewey-raw |
510 |
isfreeaccess_bool |
false |
container_title |
Iterated Gilbert mosaics |
authorswithroles_txt_mv |
Jeong, Jina @@aut@@ Park, Eungyu @@oth@@ Emelyanova, Irina @@oth@@ Pervukhina, Marina @@oth@@ Esteban, Lionel @@oth@@ Yun, Seong-Taek @@oth@@ |
publishDateDaySort_date |
2021-01-01T00:00:00Z |
hierarchy_top_id |
ELV008094314 |
dewey-sort |
3510 |
id |
ELV052479749 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV052479749</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626033337.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.petrol.2020.108028</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV052479749</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0920-4105(20)31083-4</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">31.70</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jeong, Jina</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Application of conditional generative model for sonic log estimation considering measurement uncertainty</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Well-log estimation</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Conditional variational autoencoder</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Sensitivity analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Bi-direction LSTM (Bi-LSTM)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Long short-term memory (LSTM)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Probabilistic estimation</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Park, Eungyu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Emelyanova, Irina</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pervukhina, Marina</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Esteban, Lionel</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yun, Seong-Taek</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Baccelli, Francois ELSEVIER</subfield><subfield code="t">Iterated Gilbert mosaics</subfield><subfield code="d">2019</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV008094314</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:196</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.petrol.2020.108028</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-MAT</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">31.70</subfield><subfield code="j">Wahrscheinlichkeitsrechnung</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">196</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
author |
Jeong, Jina |
spellingShingle |
Jeong, Jina ddc 510 bkl 31.70 Elsevier Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation Application of conditional generative model for sonic log estimation considering measurement uncertainty |
authorStr |
Jeong, Jina |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV008094314 |
format |
electronic Article |
dewey-ones |
510 - Mathematics |
delete_txt_mv |
keep |
author_role |
aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
topic_title |
510 VZ 31.70 bkl Application of conditional generative model for sonic log estimation considering measurement uncertainty Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation Elsevier |
topic |
ddc 510 bkl 31.70 Elsevier Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation |
topic_unstemmed |
ddc 510 bkl 31.70 Elsevier Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation |
topic_browse |
ddc 510 bkl 31.70 Elsevier Well-log estimation Elsevier Conditional variational autoencoder Elsevier Sensitivity analysis Elsevier Bi-direction LSTM (Bi-LSTM) Elsevier Long short-term memory (LSTM) Elsevier Probabilistic estimation |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
zu |
author2_variant |
e p ep i e ie m p mp l e le s t y sty |
hierarchy_parent_title |
Iterated Gilbert mosaics |
hierarchy_parent_id |
ELV008094314 |
dewey-tens |
510 - Mathematics |
hierarchy_top_title |
Iterated Gilbert mosaics |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)ELV008094314 |
title |
Application of conditional generative model for sonic log estimation considering measurement uncertainty |
ctrlnum |
(DE-627)ELV052479749 (ELSEVIER)S0920-4105(20)31083-4 |
title_full |
Application of conditional generative model for sonic log estimation considering measurement uncertainty |
author_sort |
Jeong, Jina |
journal |
Iterated Gilbert mosaics |
journalStr |
Iterated Gilbert mosaics |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
500 - Science |
recordtype |
marc |
publishDateSort |
2021 |
contenttype_str_mv |
zzz |
container_start_page |
0 |
author_browse |
Jeong, Jina |
container_volume |
196 |
class |
510 VZ 31.70 bkl |
format_se |
Elektronische Aufsätze |
author-letter |
Jeong, Jina |
doi_str_mv |
10.1016/j.petrol.2020.108028 |
dewey-full |
510 |
title_sort |
application of conditional generative model for sonic log estimation considering measurement uncertainty |
title_auth |
Application of conditional generative model for sonic log estimation considering measurement uncertainty |
abstract |
Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. |
abstractGer |
Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. |
abstract_unstemmed |
Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation. |
collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OPC-MAT |
title_short |
Application of conditional generative model for sonic log estimation considering measurement uncertainty |
url |
https://doi.org/10.1016/j.petrol.2020.108028 |
remote_bool |
true |
author2 |
Park, Eungyu Emelyanova, Irina Pervukhina, Marina Esteban, Lionel Yun, Seong-Taek |
author2Str |
Park, Eungyu Emelyanova, Irina Pervukhina, Marina Esteban, Lionel Yun, Seong-Taek |
ppnlink |
ELV008094314 |
mediatype_str_mv |
z |
isOA_txt |
false |
hochschulschrift_bool |
false |
author2_role |
oth oth oth oth oth |
doi_str |
10.1016/j.petrol.2020.108028 |
up_date |
2024-07-06T23:08:47.931Z |
_version_ |
1803872976694673408 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV052479749</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626033337.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.petrol.2020.108028</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001279.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV052479749</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0920-4105(20)31083-4</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">31.70</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jeong, Jina</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Application of conditional generative model for sonic log estimation considering measurement uncertainty</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Well-log data is a cost-effective means to characterize the petrophysical properties of a geological formation. Among the data, compressional- and shear-slowness (DTC and DTS, respectively) are the most reliable and have been widely applied in the interpretations. However, the availability of DTS data tends to be limited because of its high acquisition cost. This study proposes a method to reproduce or reconstruct the DTS data using other well-log data, such as gamma ray, neutron porosity, bulk density, and DTC. The developed method is based on the conditional variational autoencoder (CVAE) and effectively considers uncertainty associated with the variability of the measured data. The performance of this developed method is validated by applying the well-log data acquired from Satyr-5 and Callihoe-1 wells in the Northern Carnarvon Basin, Western Australia, and the prediction accuracy of the developed method is compared to recently developed data-driven methods (i.e., long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM)). The results reveal that the developed method produces a better DTS estimation than LSTM and bi-LSTM. Furthermore, the effectiveness of the proposed method remains unaltered regardless of whether the data contain a specific trend over the depth or amount of training data are insufficient. As a further application of the developed method, an uncertainty relative to DTS estimation is quantitatively obtained from Monte-Carlo estimation, which uses a trained probability model of the developed method. Sensitivity analysis reveals the high effectiveness of DTC in improving the performance of the CVAE method. From our results, we can conclude that the proposed CVAE-based method is an effective tool for improving the efficiency and accuracy of DTS estimation.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Well-log estimation</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Conditional variational autoencoder</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Sensitivity analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Bi-direction LSTM (Bi-LSTM)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Long short-term memory (LSTM)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Probabilistic estimation</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Park, Eungyu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Emelyanova, Irina</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pervukhina, Marina</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Esteban, Lionel</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yun, Seong-Taek</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Baccelli, Francois ELSEVIER</subfield><subfield code="t">Iterated Gilbert mosaics</subfield><subfield code="d">2019</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV008094314</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:196</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.petrol.2020.108028</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-MAT</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">31.70</subfield><subfield code="j">Wahrscheinlichkeitsrechnung</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">196</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
score |
7.400094 |