Seismic data conditioning and neural network-based attribute selection for enhanced fault detection

In this study of the Dorood oil field, offshore Iran, 3D seismic data were utilized to identify a complex fault pattern in the highly faulted and fractured Fahliyan Formation. To enhance data quality and improve attribute accuracy and detection power, a steering cube was first computed based on a sl...

Full description

Bibliographic Details
Main Authors: Chehrazi, A., Rahimpour-Bonab, H., Rezaee, Reza
Format: Journal Article
Published: The Geological Society and the European Association of Geoscientists & Engineers 2013
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/31392
_version_ 1848753367965237248
author Chehrazi, A.
Rahimpour-Bonab, H.
Rezaee, Reza
author_facet Chehrazi, A.
Rahimpour-Bonab, H.
Rezaee, Reza
author_sort Chehrazi, A.
building Curtin Institutional Repository
collection Online Access
description In this study of the Dorood oil field, offshore Iran, 3D seismic data were utilized to identify a complex fault pattern in the highly faulted and fractured Fahliyan Formation. To enhance data quality and improve attribute accuracy and detection power, a steering cube was first computed based on a sliding 3D Fourier analysis technique, using the concept of directivity. The steering cube, which contains dip and azimuth information for each trace, was utilized for calculation of dip-steered filters and attributes. We applied the dip-steered median filter to remove random noise and to enhance laterally continuous seismic events by filtering along the structural dip. Several fault identification attributes, such as dip, curvature, coherency and similarity, and a meta-attribute of a ridge enhancement filter, were extracted from dip-steered, noise-attenuated data. A supervised, fully connected multi-layer perceptron neural network was constructed to select and combine the most sensitive fault attributes. The neural network, trained at identified fault and non-fault locations, was applied to the whole seismic volume to generate a cube of fault probability. Interpretations of major faults and fractures were integrated with geological, reservoir engineering and production data to highlight the role of these heterogeneities on dynamic reservoir properties. Faults and fractures in the Fahliyan reservoir were identified in general to have the effect of decreasing reservoir permeability. While most of the faults recognized have locally a sealing capacity effect, when the fault throws are large enough to bring into contact the Manifa and Yamama reservoirs, they act as a conduit for fluid communication and, wherever a well crosses a major fault, early water breakthrough is observable.
first_indexed 2025-11-14T08:23:24Z
format Journal Article
id curtin-20.500.11937-31392
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:23:24Z
publishDate 2013
publisher The Geological Society and the European Association of Geoscientists & Engineers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-313922017-09-13T15:19:08Z Seismic data conditioning and neural network-based attribute selection for enhanced fault detection Chehrazi, A. Rahimpour-Bonab, H. Rezaee, Reza neural network Seismic data enhanced fault detection In this study of the Dorood oil field, offshore Iran, 3D seismic data were utilized to identify a complex fault pattern in the highly faulted and fractured Fahliyan Formation. To enhance data quality and improve attribute accuracy and detection power, a steering cube was first computed based on a sliding 3D Fourier analysis technique, using the concept of directivity. The steering cube, which contains dip and azimuth information for each trace, was utilized for calculation of dip-steered filters and attributes. We applied the dip-steered median filter to remove random noise and to enhance laterally continuous seismic events by filtering along the structural dip. Several fault identification attributes, such as dip, curvature, coherency and similarity, and a meta-attribute of a ridge enhancement filter, were extracted from dip-steered, noise-attenuated data. A supervised, fully connected multi-layer perceptron neural network was constructed to select and combine the most sensitive fault attributes. The neural network, trained at identified fault and non-fault locations, was applied to the whole seismic volume to generate a cube of fault probability. Interpretations of major faults and fractures were integrated with geological, reservoir engineering and production data to highlight the role of these heterogeneities on dynamic reservoir properties. Faults and fractures in the Fahliyan reservoir were identified in general to have the effect of decreasing reservoir permeability. While most of the faults recognized have locally a sealing capacity effect, when the fault throws are large enough to bring into contact the Manifa and Yamama reservoirs, they act as a conduit for fluid communication and, wherever a well crosses a major fault, early water breakthrough is observable. 2013 Journal Article http://hdl.handle.net/20.500.11937/31392 10.1144/petgeo2011-001 The Geological Society and the European Association of Geoscientists & Engineers restricted
spellingShingle neural network
Seismic data
enhanced fault detection
Chehrazi, A.
Rahimpour-Bonab, H.
Rezaee, Reza
Seismic data conditioning and neural network-based attribute selection for enhanced fault detection
title Seismic data conditioning and neural network-based attribute selection for enhanced fault detection
title_full Seismic data conditioning and neural network-based attribute selection for enhanced fault detection
title_fullStr Seismic data conditioning and neural network-based attribute selection for enhanced fault detection
title_full_unstemmed Seismic data conditioning and neural network-based attribute selection for enhanced fault detection
title_short Seismic data conditioning and neural network-based attribute selection for enhanced fault detection
title_sort seismic data conditioning and neural network-based attribute selection for enhanced fault detection
topic neural network
Seismic data
enhanced fault detection
url http://hdl.handle.net/20.500.11937/31392