Latest developments in seismic texture analysis for subsurface structure, facies, and reservoir characterization: A review

In exploration geology and geophysics, seismic texture is still a developing concept that has not been sufficiently known, although quite a number of different algorithms have been published in the literature. This paper provides a review of the seismic texture concepts and methodologies, focusing on latest developments in seismic amplitude texture analysis, with particular reference to the gray level co-occurrence matrix (GLCM) and the texture model regression (TMR) methods. The GLCM method evaluates spatial arrangements of amplitude samples within an analysis window using a matrix (a two-dimensional histogram) of amplitude co-occurrence. The matrix is then transformed into a suite of texture attributes, such as homogeneity, contrast, and randomness, which provide the basis for seismic facies classification. The TMR method uses a texture model as reference to discriminate among seismic features based on a linear, least-squares regression analysis between the model and the data within an analysis window. By implementing customized texture model schemes, the TMR algorithm has the flexibility to characterize subsurface geology for different purposes. A texture model with a constant phase is effective at enhancing the visibility of seismic structural fabrics, a texture model with a variable phase is helpful for visualizing seismic facies, and a texture model with variable amplitude, frequency, and size is instrumental in calibrating seismic to reservoir properties. Preliminary test case studies in the very recent past have indicated that the latest developments in seismic texture analysis have added to the existing amplitude interpretation theories and methodologies. These and future developments in seismic texture theory and methodologies will hopefully lead to a better understanding of the geologic implications of the seismic texture concept and to an improved geologic interpretation of reflection seismic amplitude.

Download Full-text

Nonlinear gray-level co-occurrence matrix texture analysis for improved seismic facies interpretation

Interpretation ◽

10.1190/int-2016-0214.1 ◽

2017 ◽

Vol 5 (3) ◽

pp. SJ31-SJ40 ◽

Cited By ~ 10

Author(s):

Haibin Di ◽

Dengliang Gao

Keyword(s):

Texture Analysis ◽

Amplitude Distribution ◽

Spatial Arrangement ◽

Seismic Facies ◽

Gray Level ◽

3D Seismic ◽

Data Set ◽

Seismic Amplitude ◽

Analysis Window ◽

Occurrence Matrix

Seismic texture analysis is a useful tool for delineating subsurface geologic features from 3D seismic surveys, and the gray-level co-occurrence matrix (GLCM) method has been popularly applied for seismic texture discrimination since its first introduction in the 1990s. The GLCM texture analysis consists of two components: (1) to rescale seismic amplitude by a user-defined number of gray levels and (2) to perform statistical analysis on the spatial arrangement of gray levels within an analysis window. Traditionally, the linear transformation is simply used for amplitude rescaling so that the original reflection patterns could be best preserved. However, the seismic features of interpretational interest often cover only a small portion of its amplitude histogram. For representing such features more effectively, it is helpful to perform a nonlinear rescaling of the amplitude distribution between different seismic features. To achieve such an objective, this study proposes a nonlinear GLCM analysis based on four types of nonlinear gray-level transformation (logarithmic, exponential, sigmoid, and logit) and investigates their implications for seismic facies interpretation. Applications to the 3D seismic data set from offshore Angola (West Africa) demonstrate the added values of the generated nonlinear GLCM attributes in better characterizing the channels, fans, and lobes in a deep-marine turbidite system.

Download Full-text

Applications of Artificial Neural Networks for Seismic Facies Classification

Journal of Petroleum Technology ◽

10.2118/0221-0068-jpt ◽

2021 ◽

Vol 73 (02) ◽

pp. 68-69

Author(s):

Chris Carpenter

Keyword(s):

Neural Network ◽

Seismic Data ◽

Reservoir Characterization ◽

Probabilistic Neural Network ◽

Oil Field ◽

Seismic Facies ◽

Data Set ◽

Full Field ◽

Facies Classification

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 200577, “Applications of Artificial Neural Networks for Seismic Facies Classification: A Case Study From the Mid-Cretaceous Reservoir in a Supergiant Oil Field,” by Ali Al-Ali, Karl Stephen, SPE, and Asghar Shams, Heriot-Watt University, prepared for the 2020 SPE Europec featured at the 82nd EAGE Conference and Exhibition, originally scheduled to be held in Amsterdam, 1-3 December. The paper has not been peer reviewed. Facies classification using data from sources such as wells and outcrops cannot capture all reservoir characterization in the interwell region. Therefore, as an alternative approach, seismic facies classification schemes are applied to reduce the uncertainties in the reservoir model. In this study, a machine-learning neural network was introduced to predict the lithology required for building a full-field Earth model for carbonate reservoirs in southern Iraq. The work and the methodology provide a significant improvement in facies classification and reveal the capability of a probabilistic neural network technique. Introduction The use of machine learning in seismic facies classification has increased gradually during the past decade in the interpretation of 3D and 4D seismic volumes and reservoir characterization work flows. The complete paper provides a literature review regarding this topic. Previously, seismic reservoir characterization has revealed the heterogeneity of the Mishrif reservoir and its distribution in terms of the pore system and the structural model. However, the main objective of this work is to classify and predict the heterogeneous facies of the carbonate Mishrif reservoir in a giant oil field using a multilayer feed-forward network (MLFN) and a probabilistic neural network (PNN) in nonlinear facies classification techniques. A related objective was to find any domain-specific causal relationships among input and output variables. These two methods have been applied to classify and predict the presence of different facies in Mishrif reservoir rock types. Case Study Reservoir and Data Set Description. The West Qurna field is a giant, multibillion-barrel oil field in the southern Mesopotamian Basin with multiple carbonate and clastic reservoirs. The overall structure of the field is a north/south trending anticline steep on the western flank and gentle on the eastern flank. Many producing reservoirs developed in this oil field; however, the Mid- Cretaceous Mishrif reservoir is the main producing reservoir. The reservoir consists of thick carbonate strata (roughly 250 m) deposited on a shallow water platform adjacent to more-distal, deeper-water nonreservoir carbonate facies developing into three stratigraphic sequence units in the second order. Mishrif facies are characterized by a porosity greater than 20% and large permeability contrast from grainstones to microporosity (10-1000 md). The first full-field 3D seismic data set was achieved over 500 km2 during 2012 and 2013 in order to plan the development of all field reservoirs. A de-tailed description of the reservoir has been determined from well logs and core and seismic data. This study is mainly based on facies log (22 wells) and high-resolution 3D seismic volume to generate seismic attributes as the input data for the training of the neural network model. The model is used to evaluate lithofacies in wells without core data but with appropriate facies logs. Also, testing was carried out in parallel with the core data to verify the results of facies classification.

Download Full-text

Application of Artificial Neural Network in seismic reservoir characterization: a case study from Offshore Nile Delta

Earth Science Informatics ◽

10.1007/s12145-021-00573-x ◽

2021 ◽

Author(s):

Adel Othman ◽

Mohamed Fathy ◽

Islam A. Mohamed

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Seismic Data ◽

Reservoir Characterization ◽

Nile Delta ◽

Reservoir Properties ◽

Seismic Amplitude ◽

Inversion Methods ◽

Amplitude Data ◽

Seismic Reservoir

AbstractThe Prediction of the reservoir characteristics from seismic amplitude data is a main challenge. Especially in the Nile Delta Basin, where the subsurface geology is complex and the reservoirs are highly heterogeneous. Modern seismic reservoir characterization methodologies are spanning around attributes analysis, deterministic and stochastic inversion methods, Amplitude Variation with Offset (AVO) interpretations, and stack rotations. These methodologies proved good outcomes in detecting the gas sand reservoirs and quantifying the reservoir properties. However, when the pre-stack seismic data is not available, most of the AVO-related inversion methods cannot be implemented. Moreover, there is no direct link between the seismic amplitude data and most of the reservoir properties, such as hydrocarbon saturation, many assumptions are imbedded and the results are questionable. Application of Artificial Neural Network (ANN) algorithms to predict the reservoir characteristics is a new emerging trend. The main advantage of the ANN algorithm over the other seismic reservoir characterization methodologies is the ability to build nonlinear relationships between the petrophysical logs and seismic data. Hence, it can be used to predict various reservoir properties in a 3D space with a reasonable amount of accuracy. We implemented the ANN method on the Sequoia gas field, Offshore Nile Delta, to predict the reservoir petrophysical properties from the seismic amplitude data. The chosen algorithm was the Probabilistic Neural Network (PNN). One well was kept apart from the analysis and used later as blind quality control to test the results.

Download Full-text

Quantitative uncertainty evaluation of seismic facies classification: A case study from northeast China

Geophysics ◽

10.1190/geo2015-0228.1 ◽

2016 ◽

Vol 81 (3) ◽

pp. B87-B99 ◽

Cited By ~ 6

Author(s):

Cheng Yuan ◽

Jingye Li ◽

Xiaohong Chen ◽

Ying Rao

Keyword(s):

Seismic Data ◽

Northeast China ◽

Reservoir Characterization ◽

Early Stage ◽

Uncertainty Propagation ◽

Seismic Facies ◽

Uncertainty Evaluation ◽

Computational Time ◽

Facies Classification ◽

Well Data

Reservoir characterization in the early stage of oilfield exploration generally has enormous uncertainty because few geophysical and well data are typically available. The uncertainty when classifying the facies with seismic data propagates throughout the processes of seismic facies classification, causing errors in the final evaluation of geologic features in an area. To quantitatively evaluate the uncertainty in seismic facies classification, we have analyzed prestack seismic data and well observations in a tight reservoir from northeast China and calculated the uncertainties throughout the process. To achieve this, the facies probabilities conditioned on different properties in each step of seismic facies classification were first derived using a probabilistic multistep inversion. Second, the associated uncertainty and maximum a posterior (MAP) of facies probabilities were evaluated by means of entropy and reconstruction rate, which assessed the degree of similarity between MAP and facies sequence within the range [0, 1]. This enabled us to investigate the influence of the uncertainty propagation on seismic facies classification. The uncertainty of the inversion results for the target reservoir was finally characterized by the calculated entropy and its indicator transform. Additionally, parameter spaces of well-log and upscaled elastic properties were restricted according to the data distribution characteristics in the crossplot. Parameter vectors that were outside the restricted scopes were excluded, reducing the computational time and uncertainty. We determined that quantitative uncertainty evaluation by entropy with a probabilistic multistep approach enabled us to explore much more details of the uncertainty propagation in the processes of seismic reservoir characterization. It should be the method of choice for risk of management and decision making in reservoir assessment.

Download Full-text

Artificial Intelligence Aided Geologic Facies Classification in Complex Carbonate Reservoirs

10.2118/204705-ms ◽

2021 ◽

Author(s):

Klemens Katterbauer ◽

Alberto Marsala ◽

Yanhui Zhang ◽

Ibrahim Hoteit

Keyword(s):

Artificial Intelligence ◽

Reservoir Characterization ◽

High Efficiency ◽

Support Vector ◽

Well Log ◽

Reservoir Properties ◽

Model Learning ◽

Field Development ◽

Facies Classification ◽

Classification Framework

Abstract Facies classification for complex reservoirs is an important step in characterizing reservoir heterogeneity and determining reservoir properties and fluid flow patterns. Predicting rock facies automatically and reliably from well log and associated reservoir measurements is therefore essential to obtain accurate reservoir characterization for field development in a timely manner. In this study, we present an artificial intelligence (AI) aided rock facies classification framework for complex reservoirs based on well log measurements. We generalize the AI-aided classification workflow into five major steps including data collection, preprocessing, feature engineering, model learning cycle, and model prediction. In particular, we automate the process of facies classification focusing on the use of a deep learning technique, convolutional neural network, which has shown outstanding performance in many scientific applications involving pattern recognition and classification. For performance analysis, we also compare the developed model with a support vector machine approach. We examine the AI-aided workflow on a large open dataset acquired from a real complex reservoir in Alberta. The dataset contains a collection of well-log measurements over a couple of thousands of wells. The experimental results demonstrate the high efficiency and scalability of the developed framework for automatic facies classification with reasonable accuracy. This is particularly useful when quick facies prediction is necessary to support real-time decision making. The AI-aided framework is easily implementable and expandable to other reservoir applications.

Download Full-text

Characterizing a turbidite system in Canterbury Basin, New Zealand, using seismic attributes and distance-preserving self-organizing maps

Interpretation ◽

10.1190/int-2015-0094.1 ◽

2016 ◽

Vol 4 (1) ◽

pp. SB79-SB89 ◽

Cited By ~ 31

Author(s):

Tao Zhao ◽

Jing Zhang ◽

Fangyu Li ◽

Kurt J. Marfurt

Keyword(s):

New Zealand ◽

Seismic Attributes ◽

Seismic Facies ◽

Seismic Attribute ◽

Self Organizing Maps ◽

Seismic Amplitude ◽

Facies Classification ◽

Turbidite System ◽

Reliable Classification ◽

Self Organizing

Recent developments in seismic attributes and seismic facies classification techniques have greatly enhanced the capability of interpreters to delineate and characterize features that are not prominent in conventional 3D seismic amplitude volumes. The use of appropriate seismic attributes that quantify the characteristics of different geologic facies can accelerate and partially automate the interpretation process. Self-organizing maps (SOMs) are a popular seismic facies classification tool that extract similar patterns embedded with multiple seismic attribute volumes. By preserving the distance in the input data space into the SOM latent space, the internal relation among data vectors on an SOM facies map is better presented, resulting in a more reliable classification. We have determined the effectiveness of the modified algorithm by applying it to a turbidite system in Canterbury Basin, offshore New Zealand. By incorporating seismic attributes and distance-preserving SOM classification, we were able to observe architectural elements that are overlooked when using a conventional seismic amplitude volume for interpretation.

Download Full-text

A knowledge-integration framework for interpreting seismic facies

Interpretation ◽

10.1190/int-2013-0057.1 ◽

2014 ◽

Vol 2 (1) ◽

pp. SA1-SA9 ◽

Cited By ~ 5

Author(s):

Iván D. Marroquín

Keyword(s):

Spatial Distribution ◽

Knowledge Integration ◽

Optimal Number ◽

Seismic Facies ◽

Reservoir Properties ◽

Integration Framework ◽

Facies Classification ◽

Combining Data ◽

Seismic Anomalies ◽

Selection Of

In recent years, the size of seismic data volumes and the number of seismic attributes available have increased. As a result, the task of recognizing seismic anomalies for the prediction of stratigraphic features or reservoir properties can be overwhelming. One way to evaluate a large amount of data and understand potential geologic trends is to automate seismic facies classification. However, the interpretation of seismic facies remains an elusive issue. Interpreters are confronted with the selection of the clustering technique and the optimal number of seismic facies that best uncover the spatial distribution of seismic facies. An interpretation framework combining data visualization with the results from various clustering techniques was evaluated. The framework allows interpreters to be directly involved in the seismic facies classification process. Because of the active participation, interpreters (1) gain insight into the detected seismic facies, (2) verify hypotheses with respect to the spatial distribution of seismic facies, (3) compare different seismic facies classification, and (4) gain more confidence with the seismic facies interpretation.

Download Full-text

Anisotropic correction of sonic logs in wells with large relative dip

Geophysics ◽

10.1190/1.2789776 ◽

2008 ◽

Vol 73 (1) ◽

pp. E1-E5 ◽

Cited By ~ 16

Author(s):

Lev Vernik

Keyword(s):

Reservoir Characterization ◽

Low Frequency ◽

P Wave ◽

Amplitude Variation With Offset ◽

Seismic Amplitude ◽

Avo Inversion ◽

Pore Pressure Prediction ◽

Siliciclastic Rocks ◽

Dip Angle ◽

Sonic Logs

Seismic reservoir characterization and pore-pressure prediction projects rely heavily on the accuracy and consistency of sonic logs. Sonic data acquisition in wells with large relative dip is known to suffer from anisotropic effects related to microanisotropy of shales and thin-bed laminations of sand, silt, and shale. Nonetheless, if anisotropy parameters can be related to shale content [Formula: see text] in siliciclastic rocks, then I show that it is straightforward to compute the anisotropy correction to both compressional and shear logs using [Formula: see text] and the formation relative dip angle. The resulting rotated P-wave sonic logs can be used to enhance time-depth ties, velocity to effective stress transforms, and low-frequency models necessary for prestack seismic amplitude variation with offset (AVO) inversion.

Download Full-text