Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea.
Seismic petro‐facies characterization in low net‐to‐gross reservoirs with poor reservoir properties such as the Snadd Formation in the Goliat field requires a multidisciplinary approach. This is especially important when the elastic properties of the desired petro‐facies significantly overlap. Pore...
Published in: | Geophysical Prospecting |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Blackwell Publishing
2018
|
Subjects: | |
Online Access: | http://hdl.handle.net/10852/65637 http://urn.nb.no/URN:NBN:no-68297 https://doi.org/10.1111/1365-2478.12654 |
id |
ftoslouniv:oai:www.duo.uio.no:10852/65637 |
---|---|
record_format |
openpolar |
spelling |
ftoslouniv:oai:www.duo.uio.no:10852/65637 2023-05-15T15:38:48+02:00 Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. ENEngelskEnglishIntegrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. Yenwongfai, Honore Dzekamelive Mondol, Nazmul Haque Faleide, Jan Inge Lecomte, Isabelle Leutscher, Johan 2018-05-21T21:08:10Z http://hdl.handle.net/10852/65637 http://urn.nb.no/URN:NBN:no-68297 https://doi.org/10.1111/1365-2478.12654 EN eng Blackwell Publishing http://urn.nb.no/URN:NBN:no-68297 Yenwongfai, Honore Dzekamelive Mondol, Nazmul Haque Faleide, Jan Inge Lecomte, Isabelle Leutscher, Johan . Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. Geophysical Prospecting. 2018 http://hdl.handle.net/10852/65637 1585767 info:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Geophysical Prospecting&rft.volume=&rft.spage=&rft.date=2018 Geophysical Prospecting doi:10.1111/1365-2478.12654 URN:NBN:no-68297 Fulltext https://www.duo.uio.no/bitstream/handle/10852/65637/1/Paper%2BIV_Yenwongfai%2Bet%2Bal%2B2018_Geophysical%2BProspecting_Accepted%2BFinal%2BManuscript.pdf 0016-8025 Journal article Tidsskriftartikkel Peer reviewed AcceptedVersion 2018 ftoslouniv https://doi.org/10.1111/1365-2478.12654 2020-06-21T08:52:15Z Seismic petro‐facies characterization in low net‐to‐gross reservoirs with poor reservoir properties such as the Snadd Formation in the Goliat field requires a multidisciplinary approach. This is especially important when the elastic properties of the desired petro‐facies significantly overlap. Pore fluid corrected endmember sand and shale depth trends have been used to generate stochastic forward models for different lithology and fluid combinations in order to assess the degree of separation of different petro‐facies. Subsequently, a spectral decomposition and blending of selected frequency volumes reveal some seismic fluvial geomorphological features. We then jointly inverted for impedance and facies within a Bayesian framework using facies‐dependent rock physics depth trends as input. The results from the inversion are then integrated into a supervised machine learning neural network for effective porosity discrimination. Probability density functions derived from stochastic forward modelling of endmember depth trends show a decreasing seismic fluid discrimination with depth. Spectral decomposition and blending of selected frequencies reveal a dominant NNE trend compared to the regional SE–NW pro‐gradational trend, and a local E–W trend potentially related to fault activity at branches of the Troms‐Finnmark Fault Complex. The facies‐based inversion captures the main reservoir facies within the limits of the seismic bandwidth. Meanwhile the effective porosity predictions from the multilayer feed forward neural network are consistent with the inverted facies model, and can be used to qualitatively highlight the cleanest regions within the inverted facies model. A combination of facies‐based inversion and neural network improves the seismic reservoir delineation of the Snadd Formation in the Goliat Field. Article in Journal/Newspaper Barents Sea Finnmark Finnmark Troms Universitet i Oslo: Digitale utgivelser ved UiO (DUO) Barents Sea Geophysical Prospecting 67 4 1020 1039 |
institution |
Open Polar |
collection |
Universitet i Oslo: Digitale utgivelser ved UiO (DUO) |
op_collection_id |
ftoslouniv |
language |
English |
description |
Seismic petro‐facies characterization in low net‐to‐gross reservoirs with poor reservoir properties such as the Snadd Formation in the Goliat field requires a multidisciplinary approach. This is especially important when the elastic properties of the desired petro‐facies significantly overlap. Pore fluid corrected endmember sand and shale depth trends have been used to generate stochastic forward models for different lithology and fluid combinations in order to assess the degree of separation of different petro‐facies. Subsequently, a spectral decomposition and blending of selected frequency volumes reveal some seismic fluvial geomorphological features. We then jointly inverted for impedance and facies within a Bayesian framework using facies‐dependent rock physics depth trends as input. The results from the inversion are then integrated into a supervised machine learning neural network for effective porosity discrimination. Probability density functions derived from stochastic forward modelling of endmember depth trends show a decreasing seismic fluid discrimination with depth. Spectral decomposition and blending of selected frequencies reveal a dominant NNE trend compared to the regional SE–NW pro‐gradational trend, and a local E–W trend potentially related to fault activity at branches of the Troms‐Finnmark Fault Complex. The facies‐based inversion captures the main reservoir facies within the limits of the seismic bandwidth. Meanwhile the effective porosity predictions from the multilayer feed forward neural network are consistent with the inverted facies model, and can be used to qualitatively highlight the cleanest regions within the inverted facies model. A combination of facies‐based inversion and neural network improves the seismic reservoir delineation of the Snadd Formation in the Goliat Field. |
format |
Article in Journal/Newspaper |
author |
Yenwongfai, Honore Dzekamelive Mondol, Nazmul Haque Faleide, Jan Inge Lecomte, Isabelle Leutscher, Johan |
spellingShingle |
Yenwongfai, Honore Dzekamelive Mondol, Nazmul Haque Faleide, Jan Inge Lecomte, Isabelle Leutscher, Johan Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. |
author_facet |
Yenwongfai, Honore Dzekamelive Mondol, Nazmul Haque Faleide, Jan Inge Lecomte, Isabelle Leutscher, Johan |
author_sort |
Yenwongfai, Honore Dzekamelive |
title |
Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. |
title_short |
Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. |
title_full |
Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. |
title_fullStr |
Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. |
title_full_unstemmed |
Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. |
title_sort |
integrating facies-based bayesian inversion and supervised machine learning for petrofacies characterisation in the snadd formation of the goliat field, sw barents sea. |
publisher |
Blackwell Publishing |
publishDate |
2018 |
url |
http://hdl.handle.net/10852/65637 http://urn.nb.no/URN:NBN:no-68297 https://doi.org/10.1111/1365-2478.12654 |
geographic |
Barents Sea |
geographic_facet |
Barents Sea |
genre |
Barents Sea Finnmark Finnmark Troms |
genre_facet |
Barents Sea Finnmark Finnmark Troms |
op_source |
0016-8025 |
op_relation |
http://urn.nb.no/URN:NBN:no-68297 Yenwongfai, Honore Dzekamelive Mondol, Nazmul Haque Faleide, Jan Inge Lecomte, Isabelle Leutscher, Johan . Integrating facies-based Bayesian inversion and supervised machine learning for petrofacies characterisation in the Snadd Formation of the Goliat Field, SW Barents Sea. Geophysical Prospecting. 2018 http://hdl.handle.net/10852/65637 1585767 info:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Geophysical Prospecting&rft.volume=&rft.spage=&rft.date=2018 Geophysical Prospecting doi:10.1111/1365-2478.12654 URN:NBN:no-68297 Fulltext https://www.duo.uio.no/bitstream/handle/10852/65637/1/Paper%2BIV_Yenwongfai%2Bet%2Bal%2B2018_Geophysical%2BProspecting_Accepted%2BFinal%2BManuscript.pdf |
op_doi |
https://doi.org/10.1111/1365-2478.12654 |
container_title |
Geophysical Prospecting |
container_volume |
67 |
container_issue |
4 |
container_start_page |
1020 |
op_container_end_page |
1039 |
_version_ |
1766370131915571200 |