Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian Gulf

This study presents an intelligent model based on probabilistic neural networks (PNN) to produce a quantitative formulation between seismic attributes and hydraulic flow units (HFUs). Neural networks have been used for the last several years to estimate reservoir properties. However, their applicati...

Full description

Bibliographic Details
Main Authors: Mohammad Amin Dezfoolian, Mohammad Ali Riahi, Ali Kadkhodaie-Ilkhchi
Format: Article
Language:English
Published: Universidad Nacional de Colombia 2013-07-01
Series:Earth Sciences Research Journal
Subjects:
Online Access:https://revistas.unal.edu.co/index.php/esrj/article/view/34000
id doaj-056db71200264b27a8be3e3ed4bcf8eb
record_format Article
spelling doaj-056db71200264b27a8be3e3ed4bcf8eb2020-11-24T22:41:28ZengUniversidad Nacional de ColombiaEarth Sciences Research Journal1794-61902339-34592013-07-0117235886Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian GulfMohammad Amin Dezfoolian0Mohammad Ali Riahi1Ali Kadkhodaie-Ilkhchi21Young Researchers Club, Science and Research Branch, Islamic Azad University, Tehran, IranDepartment of Mining Engineering, Science and Research Branch, Islamic Azad University, Tehran, IranDepartment of Mining Engineering, Science and Research Branch, Islamic Azad University, Tehran, IranThis study presents an intelligent model based on probabilistic neural networks (PNN) to produce a quantitative formulation between seismic attributes and hydraulic flow units (HFUs). Neural networks have been used for the last several years to estimate reservoir properties. However, their application for hydraulic flow unit estimation on a cube of seismic data is an interesting topic for research. The methodology for this application is illustrated using 3D seismic attributes and petrophysical and core data from 6 wells from the Kangan and Dalan gas reservoirs in the Persian Gulf basin. The methodology introduced in this study estimates HFUs from a large volume of 3D seismic data. This may increase exploration success rates and reduce costs through the application of more reliable output results in hydrocarbon exploration programs. 4 seismic attributes, including acoustic impedance, dominant fre- quency, amplitude weighted phase and instantaneous phase, are considered as the optimal inputs for pre- dicting HFUs from seismic data. The proposed technique is successfully tested in a carbonate sequence of Permian-Triassic rocks from the studied area. The results of this study demonstrate that there is a good agreement between the core and PNN-derived flow units. The PNN used in this study is successful in modeling flow units from 3D seismic data for which no core data or well log data are available.  Resumen Este estudio presenta un modelo inteligente basado en redes neuronales probabilísticas (PNN) para pro- ducir una formulación cuantitativa entre atributos sísmicos y unidades de flujo hidráulico (HFU). Las redes neuronales han sido utilizadas durante los últimos años para estimar las propiedades de reserva. Sin embargo, su aplicación para estimación de unidades de flujo hidráulico en un cubo de datos sísmicos es un tema importante de investigación. La metodología para esta aplicación está ilustrada a partir de datos tridimensionales y datos petrofísicos y de núcleo tomados en 6 pozos de las reservas de Kangan y Dalan, de la cuenca del Golfo Pérsico. La metodología introducida en este estudio estima las HFU de un gran volúmen de datos sísmicos tridimensionales. Esto podría incrementar los índices positivos de explora- ción y reducir los costos a través de una aplicación más confiable en resultados de producción para los programas de exploración en hidrocarbonos. Cuatro atributos sísmicos, obstrucción acústica, frecuencia dominante, fase de amplitud media y fase instantánea, son considerados en este trabajo como aportes claves para predecir los datos sísmicos de las HFU. La técnica propuesta ha sido evaluada exitosamente en una secuencia carbonada de rocas del Pérmicotriásico tomadas del área de estudio. Los resultados de este trabajo demuestran que hay concordancia entre la base de las PNN y las unidades derivadas de flujo. Las PNN utilizadas en este estudio son capaces de modelar unidades de flujo de datos sísmicos tridimen- sionales para los cuales no hay un centro de datos o una secuencia de datos disponible.https://revistas.unal.edu.co/index.php/esrj/article/view/34000seismic attributesseismic inversionflow zone indicatorreservoir quality indexhydraulic flow unitprobabilistic neural networks.
collection DOAJ
language English
format Article
sources DOAJ
author Mohammad Amin Dezfoolian
Mohammad Ali Riahi
Ali Kadkhodaie-Ilkhchi
spellingShingle Mohammad Amin Dezfoolian
Mohammad Ali Riahi
Ali Kadkhodaie-Ilkhchi
Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian Gulf
Earth Sciences Research Journal
seismic attributes
seismic inversion
flow zone indicator
reservoir quality index
hydraulic flow unit
probabilistic neural networks.
author_facet Mohammad Amin Dezfoolian
Mohammad Ali Riahi
Ali Kadkhodaie-Ilkhchi
author_sort Mohammad Amin Dezfoolian
title Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian Gulf
title_short Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian Gulf
title_full Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian Gulf
title_fullStr Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian Gulf
title_full_unstemmed Conversion of 3D seismic attributes to reservoir hydraulic flow units using a neural network approach: An example from the Kangan and Dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the Persian Gulf
title_sort conversion of 3d seismic attributes to reservoir hydraulic flow units using a neural network approach: an example from the kangan and dalan carbonate reservoirs, the world's largest non-associated gas reservoirs, near the persian gulf
publisher Universidad Nacional de Colombia
series Earth Sciences Research Journal
issn 1794-6190
2339-3459
publishDate 2013-07-01
description This study presents an intelligent model based on probabilistic neural networks (PNN) to produce a quantitative formulation between seismic attributes and hydraulic flow units (HFUs). Neural networks have been used for the last several years to estimate reservoir properties. However, their application for hydraulic flow unit estimation on a cube of seismic data is an interesting topic for research. The methodology for this application is illustrated using 3D seismic attributes and petrophysical and core data from 6 wells from the Kangan and Dalan gas reservoirs in the Persian Gulf basin. The methodology introduced in this study estimates HFUs from a large volume of 3D seismic data. This may increase exploration success rates and reduce costs through the application of more reliable output results in hydrocarbon exploration programs. 4 seismic attributes, including acoustic impedance, dominant fre- quency, amplitude weighted phase and instantaneous phase, are considered as the optimal inputs for pre- dicting HFUs from seismic data. The proposed technique is successfully tested in a carbonate sequence of Permian-Triassic rocks from the studied area. The results of this study demonstrate that there is a good agreement between the core and PNN-derived flow units. The PNN used in this study is successful in modeling flow units from 3D seismic data for which no core data or well log data are available.  Resumen Este estudio presenta un modelo inteligente basado en redes neuronales probabilísticas (PNN) para pro- ducir una formulación cuantitativa entre atributos sísmicos y unidades de flujo hidráulico (HFU). Las redes neuronales han sido utilizadas durante los últimos años para estimar las propiedades de reserva. Sin embargo, su aplicación para estimación de unidades de flujo hidráulico en un cubo de datos sísmicos es un tema importante de investigación. La metodología para esta aplicación está ilustrada a partir de datos tridimensionales y datos petrofísicos y de núcleo tomados en 6 pozos de las reservas de Kangan y Dalan, de la cuenca del Golfo Pérsico. La metodología introducida en este estudio estima las HFU de un gran volúmen de datos sísmicos tridimensionales. Esto podría incrementar los índices positivos de explora- ción y reducir los costos a través de una aplicación más confiable en resultados de producción para los programas de exploración en hidrocarbonos. Cuatro atributos sísmicos, obstrucción acústica, frecuencia dominante, fase de amplitud media y fase instantánea, son considerados en este trabajo como aportes claves para predecir los datos sísmicos de las HFU. La técnica propuesta ha sido evaluada exitosamente en una secuencia carbonada de rocas del Pérmicotriásico tomadas del área de estudio. Los resultados de este trabajo demuestran que hay concordancia entre la base de las PNN y las unidades derivadas de flujo. Las PNN utilizadas en este estudio son capaces de modelar unidades de flujo de datos sísmicos tridimen- sionales para los cuales no hay un centro de datos o una secuencia de datos disponible.
topic seismic attributes
seismic inversion
flow zone indicator
reservoir quality index
hydraulic flow unit
probabilistic neural networks.
url https://revistas.unal.edu.co/index.php/esrj/article/view/34000
work_keys_str_mv AT mohammadamindezfoolian conversionof3dseismicattributestoreservoirhydraulicflowunitsusinganeuralnetworkapproachanexamplefromthekangananddalancarbonatereservoirstheworldslargestnonassociatedgasreservoirsnearthepersiangulf
AT mohammadaliriahi conversionof3dseismicattributestoreservoirhydraulicflowunitsusinganeuralnetworkapproachanexamplefromthekangananddalancarbonatereservoirstheworldslargestnonassociatedgasreservoirsnearthepersiangulf
AT alikadkhodaieilkhchi conversionof3dseismicattributestoreservoirhydraulicflowunitsusinganeuralnetworkapproachanexamplefromthekangananddalancarbonatereservoirstheworldslargestnonassociatedgasreservoirsnearthepersiangulf
_version_ 1725702140131803136