Seismic facies classification using supervised convolutional neural networks and semisupervised generative adversarial networks

Geophysics ◽  
2020 ◽  
Vol 85 (4) ◽  
pp. O47-O58 ◽  
Author(s):  
Mingliang Liu ◽  
Michael Jervis ◽  
Weichang Li ◽  
Philippe Nivlet
Keyword(s):  
Neural Networks ◽  
Seismic Data ◽  
Hydrocarbon Exploration ◽  
Training Data ◽  
Seismic Facies ◽  
Generative Adversarial Networks ◽  
Complex Data ◽  
Facies Classification ◽  
Good Ability ◽  
Well Data

Mapping of seismic and lithologic facies from 3D reflection seismic data plays a key role in depositional environment analysis and reservoir characterization during hydrocarbon exploration and development. Although a variety of machine-learning methods have been developed to speed up interpretation and improve prediction accuracy, there still exist significant challenges in 3D multiclass seismic facies classification in practice. Some of these limitations include complex data representation, limited training data with labels, imbalanced facies class distribution, and lack of rigorous performance evaluation metrics. To overcome these challenges, we have developed a supervised convolutional neural network (CNN) and a semisupervised generative adversarial network (GAN) for 3D seismic facies classification in situations with sufficient and limited well data, respectively. The proposed models can predict 3D facies distribution based on actual well log data and core analysis, or other prior geologic knowledge. Therefore, they provide a more consistent and meaningful implication to seismic interpretation than commonly used unsupervised approaches. The two deep neural networks have been tested successfully on a realistic synthetic case based on an existing reservoir and a real case study of the F3 seismic data from the Dutch sector of the North Sea. The prediction results show that, with relatively abundant well data, the supervised CNN-based learning method has a good ability in feature learning from seismic data and accurately recovering the 3D facies model, whereas the semisupervised GAN is effective in avoiding overfitting in the case of extremely limited well data. The latter seems, therefore, particularly adapted to exploration or early field development stages in which labeled data from wells are still very scarce.

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

Geophysics ◽  
2016 ◽  
Vol 81 (3) ◽  
pp. B87-B99 ◽  
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.

scholarly journals Seismic facies classification and identification by competitive neural networks

Geophysics ◽  
2003 ◽  
Vol 68 (6) ◽  
pp. 1984-1999 ◽  
Author(s):  
M. M. Saggaf ◽  
M. Nafi Toksöz ◽  
M. I. Marhoon
Keyword(s):  
Neural Networks ◽  
Seismic Data ◽  
Effective Means ◽  
Synthetic Data ◽  
Low Frequency ◽  
Real Data ◽  
Seismic Facies ◽  
Automatic Identification ◽  
Facies Classification ◽  
Geologic Model

We present an approach based on competitive neural networks for the classification and identification of reservoir facies from seismic data. This approach can be adapted to perform either classification of the seismic facies based entirely on the characteristics of the seismic response, without requiring the use of any well information, or automatic identification and labeling of the facies where well information is available. The former is of prime use for oil prospecting in new regions, where few or no wells have been drilled, whereas the latter is most useful in development fields, where the information gained at the wells can be conveniently extended to the interwell regions. Cross‐validation tests on synthetic and real seismic data demonstrated that the method can be an effective means of mapping the reservoir heterogeneity. For synthetic data, the output of the method showed considerable agreement with the actual geologic model used to generate the seismic data; for the real data application, the predicted facies accurately matched those observed at the wells. Moreover, the resulting map corroborates our existing understanding of the reservoir and shows substantial similarity to the low‐frequency geologic model constructed by interpolating the well information, while adding significant detail and enhanced resolution to that model.

Multiattribute framework analysis for the identification of carbonate mounds in the Brazilian presalt zone

2019 ◽  
Vol 7 (2) ◽  
pp. T467-T476 ◽  
Author(s):  
Carlos Jesus ◽  
Maria Olho Azul ◽  
Wagner Moreira Lupinacci ◽  
Leandro Machado
Keyword(s):  
Seismic Data ◽  
High Density ◽  
Seismic Facies ◽  
Reservoir Quality ◽  
Framework Analysis ◽  
Carbonate Mounds ◽  
Facies Classification ◽  
Static Modeling ◽  
Well Data ◽  
Low Amplitude

Carbonate mounds, as described herein, often present seismic characteristics such as low amplitude and a high density of faults and fractures, which can easily be oversampled and blur other rock features in simple geobody extraction processes. We have developed a workflow for combining geometric attributes and hybrid spectral decomposition (HSD) to efficiently identify good-quality reservoirs in carbonate mounds within the complex environment of the Brazilian presalt zone. To better identify these reservoirs within the seismic volume of carbonate mounds, we divide our methodology into four stages: seismic data acquisition and processing overview, preconditioning of seismic data using structural-oriented filtering and imaging enhancement, calculation of seismic attributes, and classification of seismic facies. Although coherence and curvature attributes are often used to identify high-density fault and fracture zones, representing one of the most important features of carbonate mounds, HSD is necessary to discriminate low-amplitude carbonate mounds (good reservoir quality) from low-amplitude clay zones (nonreservoir). Finally, we use a multiattribute facies classification to generate a geologically significant outcome and to guide a final geobody extraction that is calibrated by well data and that can be used as a spatial indicator of the distribution of good reservoir quality for static modeling.

scholarly journals Application of Musical Information Retrieval (MIR) Techniques to Seismic Facies Classification. Examples in Hydrocarbon Exploration

2016 ◽  
Vol 2 (4) ◽  
pp. 413-425 ◽  
Author(s):  
Paolo Dell’Aversana ◽  
◽  
Gianluca Gabbriellini ◽  
Alfonso Iunio Marini ◽  
Alfonso Amendola
Keyword(s):  
Information Retrieval ◽  
Hydrocarbon Exploration ◽  
Seismic Facies ◽  
Facies Classification

Applications of Artificial Neural Networks for Seismic Facies Classification

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.

A comparison of classification techniques for seismic facies recognition

2015 ◽  
Vol 3 (4) ◽  
pp. SAE29-SAE58 ◽  
Author(s):  
Tao Zhao ◽  
Vikram Jayaram ◽  
Atish Roy ◽  
Kurt J. Marfurt
Keyword(s):  
Seismic Data ◽  
Gaussian Mixture ◽  
Seismic Facies ◽  
Support Vector ◽  
3D Seismic ◽  
Generative Topographic Mapping ◽  
Learning Methods ◽  
Facies Classification ◽  
Data Volume ◽  
3D Seismic Data

During the past decade, the size of 3D seismic data volumes and the number of seismic attributes have increased to the extent that it is difficult, if not impossible, for interpreters to examine every seismic line and time slice. To address this problem, several seismic facies classification algorithms including [Formula: see text]-means, self-organizing maps, generative topographic mapping, support vector machines, Gaussian mixture models, and artificial neural networks have been successfully used to extract features of geologic interest from multiple volumes. Although well documented in the literature, the terminology and complexity of these algorithms may bewilder the average seismic interpreter, and few papers have applied these competing methods to the same data volume. We have reviewed six commonly used algorithms and applied them to a single 3D seismic data volume acquired over the Canterbury Basin, offshore New Zealand, where one of the main objectives was to differentiate the architectural elements of a turbidite system. Not surprisingly, the most important parameter in this analysis was the choice of the correct input attributes, which in turn depended on careful pattern recognition by the interpreter. We found that supervised learning methods provided accurate estimates of the desired seismic facies, whereas unsupervised learning methods also highlighted features that might otherwise be overlooked.

STUDY ON THE PARAMETERIZATION RESPONSE OF PROBABILISTIC NEURAL NETWORKS FOR SEISMIC FACIES CLASSIFICATION IN THE GULF OF MEXICO

2021 ◽  
pp. 1-105
Author(s):  
Diana Salazar Florez ◽  
Heather Bedle
Keyword(s):  
Neural Networks ◽  
Seismic Facies ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Small Scale ◽  
Probabilistic Neural Networks ◽  
Computational Costs ◽  
Facies Classification ◽  
Learning Techniques ◽  
The Impact

Nowadays, there are many unsupervised and supervised machine learning techniques available for performing seismic facies classification. However, those classification methods either demand high computational costs or do not provide an accurate measure of confidence. Probabilistic neural networks (PNNs) overcome these limitations and have demonstrated their superiority among other algorithms. PNNs have been extensively applied for some prediction tasks, but not well studied regarding the prediction of seismic facies volumes using seismic attributes. We explore the capability of the PNN algorithm when classifying large- and small-scale seismic facies. Additionally, we evaluate the impact of user-chosen parameters on the final classification volumes. After performing seven tests, each with a parameter variation, we assess the impact of the parameter change on the resultant classification volumes. We show that the processing task can have a significant impact on the classification volumes, but also how the most geologically complex areas are the most challenging for the algorithm. Moreover, we demonstrate that even if the PNN technique is performing and producing considerably accurate results, it is possible to overcome those limitations and significantly improve the final classification volumes by including the geological insight provided by the geoscientist. We conclude by proposing a new workflow that can guide future geoscientists interested in applying PNNs, to obtain better seismic facies classification volumes by considering some initial steps and advice.

Sign in / Sign up

Export Citation Format

Share Document