Applications of Machine Learning for Geoscientists – Permian Basin

Applications of Machine Learning for Geoscientists – Permian Basin

By Carrie Laudon
Published with permission: Permian Basin Geophysical Society 60th Annual Exploration Meeting
May 2019

Abstract

Over the last few years, because of the increase in low-cost computer power, individuals and companies have stepped up investigations into the use of machine learning in many areas of E&P. For the geosciences, the emphasis has been in reservoir characterization, seismic data processing, and to a lesser extent interpretation. The benefits of using machine learning (whether supervised or unsupervised) have been demonstrated throughout the literature, and yet the technology is still not a standard workflow for most seismic interpreters. This lack of uptake can be attributed to several factors, including a lack of software tools, clear and well-defined case histories and training. Fortunately, all these factors are being mitigated as the technology matures. Rather than looking at machine learning as an adjunct to the traditional interpretation methodology, machine learning techniques should be considered the first step in the interpretation workflow.

By using statistical tools such as Principal Component Analysis (PCA) and Self Organizing Maps (SOM) a multi-attribute 3D seismic volume can be “classified”. The PCA reduces a large set of seismic attributes both instantaneous and geometric, to those that are the most meaningful. The output of the PCA serves as the input to the SOM, a form of unsupervised neural network, which, when combined with a 2D color map facilitates the identification of clustering within the data volume. When the correct “recipe” is selected, the clustered or classified volume allows the interpreter to view and separate geological and geophysical features that are not observable in traditional seismic amplitude volumes. Seismic facies, detailed stratigraphy, direct hydrocarbon indicators, faulting trends, and thin beds are all features that can be enhanced by using a classified volume.

The tuning-bed thickness or vertical resolution of seismic data traditionally is based on the frequency content of the data and the associated wavelet. Seismic interpretation of thin beds routinely involves estimation of tuning thickness and the subsequent scaling of amplitude or inversion information below tuning. These traditional below-tuning-thickness estimation approaches have limitations and require assumptions that limit accuracy. The below tuning effects are a result of the interference of wavelets, which are a function of the geology as it changes vertically and laterally. However, numerous instantaneous attributes exhibit effects at and below tuning, but these are seldom incorporated in thin-bed analyses. A seismic multi-attribute approach employs self-organizing maps to identify natural clusters from combinations of attributes that exhibit below-tuning effects. These results may exhibit changes as thin as a single sample interval in thickness. Self-organizing maps employed in this fashion analyze associated seismic attributes on a sample-by-sample basis and identify the natural patterns or clusters produced by thin beds. Examples of this approach to improve stratigraphic resolution in both the Eagle Ford play, and the Niobrara reservoir of the Denver-Julesburg Basin will be used to illustrate the workflow.

Introduction

Seismic multi-attribute analysis has always held the promise of improving interpretations via the integration of attributes which respond to subsurface conditions such as stratigraphy, lithology, faulting, fracturing, fluids, pressure, etc. The benefits of using machine learning (whether supervised or unsupervised) has been demonstrated throughout the literature and yet the technology is still not a standard workflow for most seismic interpreters. This lack of uptake can be attributed to several factors, including a lack of software tools, clear and well-defined case histories, and training. This paper focuses on an unsupervised machine learning workflow utilizing Self-Organizing Maps (Kohonen, 2001) in combination with Principal Component Analysis to produce classified seismic volumes from multiple instantaneous attribute volumes. The workflow addresses several significant issues in seismic interpretation: it analyzes large amounts of data simultaneously; it determines relationships between different types of data; it is sample based and produces high-resolution results and, reveals geologic features that are difficult to see in conventional approaches.

Principal Component Analysis (PCA)

Multi-dimensional analysis and multi-attribute analysis go hand in hand. Because individuals are grounded in three-dimensional space, it is difficult to visualize what data in a higher number dimensional space looks like. Fortunately, mathematics doesn’t have this limitation and the results can be easily understood with conventional 2D and 3D viewers.

Working with multiple instantaneous or geometric seismic attributes generates tremendous volumes of data. These volumes contain huge numbers of data points which may be highly continuous, greatly redundant, and/or noisy. (Coleou et al., 2003). Principal Component Analysis (PCA) is a linear technique for data reduction which maintains the variation associated with the larger data sets (Guo and others, 2009; Haykin, 2009; Roden and others, 2015). PCA can separate attribute types by frequency, distribution, and even character. PCA technology is used to determine which attributes may be ignored due to their very low impact on neural network solutions and which attributes are most prominent in the data. Figure 1 illustrates the analysis of a data cluster in two directions, offset by 90 degrees. The first principal component (eigenvector 1) analyses the data cluster along the longest axis. The second principal component (eigenvector 2) analyses the data cluster variations perpendicular to the first principal component. As stated in the diagram, each eigenvector is associated with an eigenvalue which shows how much variance there is in the data.

two attribute data set

Figure 1. Two attribute data set illustrating the concept of PCA

The next step in PCA analysis is to review the eigen spectrum to select the most prominent attributes in a data set. The following example is taken from a suite of instantaneous attributes over the Niobrara formation within the Denver­ Julesburg Basin. Results for eigenvectors 1 are shown with three attributes: sweetness, envelope and relative acoustic impedance being the most prominent.

two attribute data set

Figure 2. Results from PCA for first eigenvector in a seismic attribute data set

Utilizing a cutoff of 60% in this example, attributes were selected from PCA for input to the neural network classification. For the Niobrara, eight instantaneous attributes from the four of the first six eigenvectors were chosen and are shown in Table 1. The PCA allowed identification of the most significant attributes from an initial group of 19 attributes.

Results from PCA for Niobrara Interval

Table 1: Results from PCA for Niobrara Interval shows which instantaneous attributes will be used in a Self-Organizing Map (SOM).

Self-Organizing Maps

Teuvo Kohonen, a Finnish mathematician, invented the concepts of Self-Organizing Maps (SOM) in 1982 (Kohonen, T., 2001). Self-Organizing Maps employ the use of unsupervised neural networks to reduce very high dimensions of data to a classification volume that can be easily visualized (Roden and others, 2015). Another important aspect of SOMs is that every seismic sample is used as input to classification as opposed to wavelet-based classification.

Figure 3 diagrams the SOM concept for 10 attributes derived from a 3D seismic amplitude volume. Within the 3D seismic survey, samples are first organized into attribute points with similar properties called natural clusters in attribute space. Within each cluster new, empty, multi-attribute samples, named neurons, are introduced. The SOM neurons will seek out natural clusters of like characteristics in the seismic data and produce a 2D mesh that can be illustrated with a two- dimensional color map. In other words, the neurons “learn” the characteristics of a data cluster through an iterative process (epochs) of cooperative than competitive training. When the learning is completed each unique cluster is assigned to a neuron number and each seismic sample is now classified (Smith, 2016).

two attribute data set

Figure 3. Illustration of the concept of a Self-Organizing Map

Figures 4 and 5 show a simple example using 2 attributes, amplitude, and Hilbert transform on a synthetic example. Synthetic reflection coefficients are convolved with a simple wavelet, 100 traces created, and noise added. When the attributes are cross plotted, clusters of points can be seen in the cross plot. The colored cross plot shows the attributes after SOM classification into 64 neurons with random colors assigned. In Figure 5, the individual clusters are identified and mapped back to the events on the synthetic. The SOM has correctly distinguished each event in the synthetic.

Two attribute synthetic example of a Self-Organizing Map

Figure 4. Two attribute synthetic example of a Self-Organizing Map. The amplitude and Hilbert transform are cross plotted. The colored cross plot shows the attributes after classification into 64 neurons by SOM.

Synthetic SOM example

Figure 5. Synthetic SOM example with neurons identified by number and mapped back to the original synthetic data

Results for Niobrara and Eagle Ford

In 2018, Geophysical Insights conducted a proof of concept on 100 square miles of multi-client 3D data jointly owned by Geophysical Pursuit, Inc. (GPI) and Fairfield Geotechnologies (FFG) in the Denver¬ Julesburg Basin (DJ). The purpose of the study is to evaluate the effectiveness of a machine learning workflow to improve resolution within the reservoir intervals of the Niobrara and Codell formations, the primary targets for development in this portion of the basin. An amplitude volume was resampled from 2 ms to 1 ms and along with horizons, loaded into the Paradise® machine learning application and attributes generated. PCA was used to identify which attributes were most significant in the data, and these were used in a SOM to evaluate the interval Top Niobrara to Greenhorn (Laudon and others, 2019).

Figure 6 shows results of an 8X8 SOM classification of 8 instantaneous attributes over the Niobrara interval along with the original amplitude data. Figure 7 is the same results with a well composite focused on the B chalk, the best section of the reservoir, which is difficult to resolve with individual seismic attributes. The SOM classification has resolved the chalk bench as well as other stratigraphic features within the interval.

North-South Inline showing the original amplitude data (upper) and the 8X8 SOM result (lower) from Top Niobrara

Figure 6. North-South Inline showing the original amplitude data (upper) and the 8X8 SOM result (lower) from Top Niobrara through Greenhorn horizons. Seismic data is shown courtesy of GPI and FFG.

8X8 Instantaneous SOM through Rotharmel 11-33 with well log composite

Figure 7. 8X8 Instantaneous SOM through Rotharmel 11-33 with well log composite. The B bench, highlighted in green on the wellbore, ties the yellow-red-yellow sequence of neurons. Seismic data is shown courtesy of GPI and FFG

 

8X8 SOM results through the Eagle Ford

Figure 8. 8X8 SOM results through the Eagle Ford. The primary target, the Lower Eagle Ford shale had 16 neuron classes over 14-29 milliseconds of data. Seismic data shown courtesy of Seitel.

The results shown in Figure 9 reveal non-layer cake facies bands that include details in the Eagle )RUG,v basal clay-rich shale, high resistivity and low resistivity Eagle Ford shale objectives, the Eagle Ford ash, and the upper Eagle Ford marl, which are overlain disconformably by the Austin Chalk.

Eagle Ford SOM classification shown with well results

Figure 9. Eagle Ford SOM classification shown with well results. The SOM resolves a high resistivity interval, overlain by a thin ash layer and finally a low resistivity layer. The SOM also resolves complex 3-dimensional relationships between these facies

Convolutional Neural Networks (CNN)

A promising development in machine learning is supervised classification via the applications of convolutional neural networks (CNNs). Supervised methods have, in the past, not been efficient due to the laborious task of training the neural network. CNN is a deep learning seismic classification. We apply CNN to fault detection on seismic data. The examples that follow show CNN fault detection results which did not require any interpreter picked faults for training, rather the network was trained using synthetic data. Two results are shown, one from the North Sea, Figure 10, and one from the Great South Basin, New Zealand, Figure 11.

Side by side comparison of coherence attribute to CNN fault probability attribute, North Sea

Figure 10. Side by side comparison of coherence attribute to CNN fault probability attribute, North Sea

Side by side comparison of coherence attribute to CNN fault probability attribute, North Sea

Figure 11. Comparison of Coherence to CNN fault probability attribute, New Zealand

Conclusions

Advances in compute power and algorithms are making the use of machine learning available on the desktop to seismic interpreters to augment their interpretation workflow. Taking advantage of today’s computing technology, visualization techniques, and an understanding of machine learning as applied to seismic data, PCA combined with SOMs efficiently distill multiple seismic attributes into classification volumes. When applied on a multi-attribute seismic sample basis, SOM is a powerful nonlinear cluster analysis and pattern recognition machine learning approach that helps interpreters identify geologic patterns in the data and has been able to reveal stratigraphy well below conventional tuning thickness.

In the fault interpretation domain, recent development of a Convolutional Neural Network that works directly on amplitude data shows promise to efficiently create fault probability volumes without the requirement of a labor-intensive training effort.

References

Coleou, T., M. Poupon, and A. Kostia, 2003, Unsupervised seismic facies classification: A review and comparison of techniques and implementation: The Leading Edge, 22, 942–953, doi: 10.1190/1.1623635.

Guo, H., K. J. Marfurt, and J. Liu, 2009, Principal component spectral analysis: Geophysics, 74, no. 4, 35–43.

Haykin, S., 2009. Neural networks and learning machines, 3rd ed.: Pearson

Kohonen, T., 2001,Self organizing maps: Third extended addition, Springer, Series in Information Services, Vol. 30.

Laudon, C., Stanley, S., and Santogrossi, P., 2019, Machine Leaming Applied to 3D Seismic Data from the Denver-Julesburg Basin Improves Stratigraphic Resolution in the Niobrara, URTeC 337, in press

Roden, R., and Santogrossi, P., 2017, Significant Advancements in Seismic Reservoir Characterization with Machine Learning, The First, v. 3, p. 14-19

Roden, R., Smith, T., and Sacrey, D., 2015, Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing maps, Interpretation, Vol. 3, No. 4, p. SAE59-SAE83.

Santogrossi, P., 2017, Classification/Corroboration of Facies Architecture in the Eagle Ford Group: A Case Study in Thin Bed Resolution, URTeC 2696775, doi 10.15530-urtec-2017-<2696775>.

Seismic Facies Classification Using Deep Convolutional Neural Networks

Seismic Facies Classification Using Deep Convolutional Neural Networks

By Tao Zhao
Published with permission: SEG International Exposition and 88th Annual Meeting
October 2018

Summary

Convolutional neural networks (CNNs) is a type of supervised learning technique that can be directly applied to amplitude data for seismic data classification. The high flexibility in CNN architecture enables researchers to design different models for specific problems. In this study, I introduce an encoder-decoder CNN model for seismic facies classification, which classifies all samples in a seismic line simultaneously and provides superior seismic facies quality comparing to the traditional patch-based CNN methods. I compare the encoder-decoder model with a traditional patch- based model to conclude the usability of both CNN architectures.

Introduction

With the rapid development in GPU computing and success obtained in computer vision domain, deep learning techniques, represented by convolutional neural networks (CNNs), start to entice seismic interpreters in the application of supervised seismic facies classification. A comprehensive review of deep learning techniques is provided in LeCun et al. (2015). Although still in its infancy, CNN-based seismic classification is successfully applied on both prestack (Araya-Polo et al., 2017) and poststack (Waldeland and Solberg, 2017; Huang et al., 2017; Lewis and Vigh, 2017) data for fault and salt interpretation, identifying different wave characteristics (Serfaty et al., 2017), as well as estimating velocity models (Araya-Polo et al., 2018).

The main advantages of CNN over other supervised classification methods are its spatial awareness and automatic feature extraction. For image classification problems, other than using the intensity values at each pixel individually, CNN analyzes the patterns among pixels in an image, and automatically generates features (in seismic data, attributes) suitable for classification. Because seismic data are 3D tomographic images, we would expect CNN to be naturally adaptable to seismic data classification. However, there are some distinct characteristics in seismic classification that makes it more challenging than other image classification problems. Firstly, classical image classification aims at distinguishing different images, while seismic classification aims at distinguishing different geological objects within the same image. Therefore, from an image processing point of view, instead of classification, seismic classification is indeed a segmentation problem (partitioning an image into blocky pixel shapes with a coarser set of colors). Secondly, training data availability for seismic classification is much sparser comparing to classical

image classification problems, for which massive data are publicly available. Thirdly, in seismic data, all features are represented by different patterns of reflectors, and the boundaries between different features are rarely explicitly defined. In contrast, features in an image from computer artwork or photography are usually well-defined. Finally, because of the uncertainty in seismic data, and the nature of manual interpretation, the training data in seismic classification is always contaminated by noise.

To address the first challenge, until today, most, if not all, published studies on CNN-based seismic facies classification perform classification on small patches of data to infer the class label of the seismic sample at the patch center. In this fashion, seismic facies classification is done by traversing through patches centered at every sample in a seismic volume. An alternative approach, although less discussed, is to use CNN models designed for image segmentation tasks (Long et al., 2015; Badrinarayanan et al., 2017; Chen et al., 2018) to obtain sample-level labels in a 2D profile (e.g. an inline) simultaneously, then traversing through all 2D profiles in a volume.

In this study, I use an encoder-decoder CNN model as an implementation of the aforementioned second approach. I apply both the encoder-decoder model and patch-based model to seismic facies classification using data from the North Sea, with the objective of demonstrating the strengths and weaknesses of the two CNN models. I conclude that the encoder-decoder model provides much better classification quality, whereas the patch-based model is more flexible on training data, possibly making it easier to use in production.

The Two Convolutional Neural Networks (CNN) Models

Patch-based model

A basic patch-based model consists of several convolutional layers, pooling (downsampling) layers, and fully-connected layers. For an input image (for seismic data, amplitudes in a small 3D window), a CNN model first automatically extracts several high-level abstractions of the image (similar to seismic attributes) using the convolutional and pooling layers, then classifies the extracted attributes using the fully- connected layers, which are similar to traditional multilayer perceptron networks. The output from the network is a single value representing the facies label of the seismic sample at the center of the input patch. An example of patch-based model architecture is provided in Figure 1a. In this example, the network is employed to classify salt versus non-salt from seismic amplitude in the SEAM synthetic data (Fehler and Larner, 2008). One input instance is a small patch of data bounded by the red box, and the corresponding output is a class label for this whole patch, which is then assigned to the sample at the patch center. The sample marked as the red dot is classified as non-salt.

CNN architecture patch-based model

Figure 1. Sketches for CNN architecture of a) 2D patch-based model and b) encoder-decoder model. In the 2D patch-based model, each input data instance is a small 2D patch of seismic amplitude centered at the sample to be classified. The corresponding output is then a class label for the whole 2D patch (in this case, non-salt), which is usually assigned to the sample at the center. In the encoder-decoder model, each input data instance is a whole inline (or crossline/time slice) of seismic amplitude. The corresponding output is a whole line of class labels, so that each sample is assigned a label (in this case, some samples are salt and others are non-salt). Different types of layers are denoted in different colors, with layer types marked at their first appearance in the network. The size of the cuboids approximately represents the output size of each layer.

Encoder-decoder model

Encoder-decoder is a popular network structure for tackling image segmentation tasks. Encoder-decoder models share a similar idea, which is first extracting high level abstractions of input images using convolutional layers, then recovering sample-level class labels by “deconvolution” operations. Chen et al. (2018) introduce a current state-of-the-art encoder-decoder model while concisely reviewed some popular predecessors. An example of encoder-decoder model architecture is provided in Figure 1b. Similar to the patch-based example, this encoder-decoder network is employed to classify salt versus non-salt from seismic amplitude in the SEAM synthetic data. Unlike the patch- based network, in the encoder-decoder network, one input instance is a whole line of seismic amplitude, and the corresponding output is a whole line of class labels, which has the same dimension as the input data. In this case, all samples in the middle of the line are classified as salt (marked in red), and other samples are classified as non-salt (marked in white), with minimum error.

Application of the Two CNN Models

For demonstration purpose, I use the F3 seismic survey acquired in the North Sea, offshore Netherlands, which is freely accessible by the geoscience research community. In this study, I am interested to automatically extract seismic facies that have specific seismic amplitude patterns. To remove the potential disagreement on the geological meaning of the facies to extract, I name the facies purely based on their reflection characteristics. Table 1 provides a list of extracted facies. There are eight seismic facies with distinct amplitude patterns, another facies (“everything else”) is used for samples not belonging to the eight target facies.

Facies numberFacies name
1Varies amplitude steeply dipping
2Random
3Low coherence
4Low amplitude deformed
5Low amplitude dipping
6High amplitude deformed
7Moderate amplitude continuous
8Chaotic
0Everything else

To generate training data for the seismic facies listed above, different picking scenarios are employed to compensate for the different input data format required in the two CNN models (small 3D patches versus whole 2D lines). For the patch-based model, 3D patches of seismic amplitude data are extracted around seed points within some user-defined polygons. There are approximately 400,000 3D patches of size 65×65×65 generated for the patch-based model, which is a reasonable amount for seismic data of this size. Figure 2a shows an example line on which seed point locations are defined in the co-rendered polygons.

The encoder-decoder model requires much more effort for generating labeled data. I manually interpret the target facies on 40 inlines across the seismic survey and use these for building the network. Although the total number of seismic samples in 40 lines are enormous, the encoder-decoder model only considers them as 40 input instances, which in fact are of very small size for a CNN network. Figure 2b shows an interpreted line which is used in training the network

In both tests, I randomly use 90% of the generated training data to train the network and use the remaining 10% for testing. On an Nvidia Quadro M5000 GPU with 8GB memory, the patch-based model takes about 30 minutes to converge, whereas the encoder-decoder model needs about 500 minutes. Besides the faster training, the patch-based model also has a higher test accuracy at almost 100% (99.9988%, to be exact) versus 94.1% from the encoder- decoder model. However, this accuracy measurement is sometimes a bit misleading. For a patch-based model, when picking the training and testing data, interpreters usually pick the most representative samples of each facies for which they have the most confidence, resulting in high quality training (and testing) data that are less noisy, and most of the ambiguous samples which are challenging for the classifier are excluded from testing. In contrast, to use an encoder-decoder model, interpreters have to interpret all the target facies in a training line. For example, if the target is faults, one needs to pick all faults in a training line, otherwise unlabeled faults will be considered as “non-fault” and confuse the classifier. Therefore, interpreters have to make some not-so-confident interpretation when generating training and testing data. Figure 2c and 2d show seismic facies predicted from the two CNN models on the same line shown in Figure 2a and 2b. We observe better defined facies from the encoder-decoder model compared to the patch- based model.

Figure 3 shows prediction results from the two networks on a line away from the training lines, and Figure 4 shows prediction results from the two networks on a crossline. Similar to the prediction results on the training line, comparing to the patch-based model, the encoder-decoder model provides facies as cleaner geobodies that require much less post-editing for regional stratigraphic classification (Figure 5). This can be attributed to an encoder-decoder model that is able to capture the large scale spatial arrangement of facies, whereas the patch-based model only senses patterns in small 3D windows. To form such windows, the patch-based model also needs to pad or simply skip samples close to the edge of a 3D seismic volume. Moreover, although the training is much faster in a patch-based model, the prediction stage is very computationally intensive, because it processes data size N×N×N times of the original seismic volume (N is the patch size along each dimension). In this study, the patch-based method takes about 400 seconds to predict a line, comparing to less than 1 second required in the encoder-decoder model.

Conclusion

In this study, I compared two types of CNN models in the application of seismic facies classification. The more commonly used patch-based model requires much less effort in generating labeled data, but the classification result is suboptimal comparing to the encoder-decoder model, and the prediction stage can be very time consuming. The encoder-decoder model generates superior classification result at near real-time speed, at the expense of more tedious labeled data picking and longer training time.

Acknowledgements

The author thanks Geophysical Insights for the permission to publish this work. Thank dGB Earth Sciences for providing the F3 North Sea seismic data to the public, and ConocoPhillips for sharing the MalenoV project for public use, which was referenced when generating the training data. The CNN models discussed in this study are implemented in TensorFlow, an open source library from Google.

Figure 2. Example of seismic amplitude co-rendered with training data picked on inline 340 used for a) patch-based model and b) encoder-decoder model. The prediction result from c) patch-based model, and d) from the encoder-decoder model. Target facies are colored in colder to warmer colors in the order shown in Table 1. Compare Facies 5, 6 and 8.

Figure 3. Prediction results from the two networks on a line away from the training lines. a) Predicted facies from the patch-based model. b) Predicted facies from the encoder-decoder based model. Target facies are colored in colder to warmer colors in the order shown in Table 1. The yellow dotted line marks the location of the crossline shown in Figure 4. Compare Facies 1, 5 and 8.

Figure 4. Prediction results from the two networks on a crossline. a) Predicted facies from the patch-based model. b) Predicted facies from the encoder-decoder model. Target facies are colored in colder to warmer colors in the order shown in Table 1. The yellow dotted lines mark the location of the inlines shown in Figure 2 and 3. Compare Facies 5 and 8.

Figure 5. Volumetric display of the predicted facies from the encoder-decoder model. The facies volume is visually cropped for display purpose. An inline and a crossline of seismic amplitude co-rendered with predicted facies are also displayed to show a broader distribution of the facies. Target facies are colored in colder to warmer colors in the order shown in Table 1.

References

Araya-Polo, M., T. Dahlke, C. Frogner, C. Zhang, T. Poggio, and D. Hohl, 2017, Automated fault detection without seismic processing: The Leading Edge, 36, 208–214.

Araya-Polo, M., J. Jennings, A. Adler, and T. Dahlke, 2018, Deep-learning tomography: The Leading Edge, 37, 58–66.

Badrinarayanan, V., A. Kendall, and R. Cipolla, 2017, SegNet: A deep convolutional encoder-decoder architecture for image segmentation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 2481–2495.

Chen, L. C., G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, 2018, DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs: IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834–848.

Chen, L. C., Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, 2018, Encoder-decoder with atrous separable convolution for semantic image segmentation: arXiv preprint, arXiv:1802.02611v2.

Fehler, M., and K. Larner, 2008, SEG advanced modeling (SEAM): Phase I first year update: The Leading Edge, 27, 1006–1007.

Huang, L., X. Dong, and T. E. Clee, 2017, A scalable deep learning platform for identifying geologic features from seismic attributes: The Leading Edge, 36, 249–256.

LeCun, Y., Y. Bengio, and G. Hinton, 2015, Deep learning: Nature, 521, 436–444.

Lewis, W., and D. Vigh, 2017, Deep learning prior models from seismic images for full-waveform inversion: 87th Annual International Meeting, SEG, Expanded Abstracts, 1512–1517.

Long, J., E. Shelhamer, and T. Darrell, 2015, Fully convolutional networks for semantic segmentation: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431–3440.

Serfaty, Y., L. Itan, D. Chase, and Z. Koren, 2017, Wavefield separation via principle component analysis and deep learning in the local angle domain: 87th Annual International Meeting, SEG, Expanded Abstracts, 991–995.

Waldeland, A. U., and A. H. S. S. Solberg, 2017, Salt classification using deep learning: 79th Annual International Conference and Exhibition, EAGE, Extended Abstracts, Tu-B4-12.

A Fault Detection Workflow Using Deep Learning and Image Processing

A Fault Detection Workflow Using Deep Learning and Image Processing

By Tao Zhao
Published with permission: SEG International Exposition and 88th Annual Meeting
October 2018

Summary

Within the last a couple of years, deep learning techniques, represented by convolutional neural networks (CNNs), have been applied to fault detection problems on seismic data with an impressive outcome. As is true for all supervised learning techniques, the performance of a CNN fault detector highly depends on the training data, and post-classification regularization may greatly improve the result. Sometimes, a pure CNN-based fault detector that works perfectly on synthetic data may not perform well on field data. In this study, we investigate a fault detection workflow using both CNN and directional smoothing/sharpening. Applying both on a realistic synthetic fault model based on the SEAM (SEG Advanced Modeling) model and also field data from the Great South Basin, offshore New Zealand, we demonstrate that the proposed fault detection workflow can perform well on challenging synthetic and field data.

Introduction

Benefited from its high flexibility in network architecture, convolutional neural networks (CNNs) are a supervised learning technique that can be designed to solve many challenging problems in exploration geophysics. Among these problems, detection of particular seismic facies of interest might be the most straightforward application of CNNs. The first published study applying CNN on seismic data might be Waldeland and Solberg (2017), in which the authors used a CNN model to classify salt versus non-salt features in a seismic volume. At about the same time as Waldeland and Solberg (2017), Araya-Polo et al. (2017) and Huang et al. (2017) reported success in fault detection using CNN models.

From a computer vision perspective, in seismic data, faults are a special group of edges. CNN has been applied to more general edge detection problems with great success (El- Sayed et al., 2013; Xie and Tu, 2015). However, faults in seismic data are fundamentally different from edges in images used in computer vision domain. The regions separated by edges in a traditional computer vision image are relatively homogeneous, whereas in seismic data such regions are defined by patterns of reflectors. Moreover, not all edges in seismic data are faults. In practice, although providing excellent fault images, traditional edge detection attributes such as coherence (Marfurt et al., 1999) are also sensitive to stratigraphic edges such as unconformities, channel banks, and karst collapses. Wu and Hale (2016) proposed a brilliant workflow for automatically extracting fault surfaces, in which a crucial step is computing the fault likelihood. CNN-based fault detection methods can be used as an alternative approach to generate such fault likelihood volumes, and the fault strike and dip can be then computed from the fault likelihood.

One drawback of supervised machine learning-based fault detection is its brute-force nature, meaning that instead of detecting faults following geological/geophysical principles, the detection purely depends on the training data. In reality, we will never have training data that covers all possible appearances of faults in seismic data, nor are our data noise- free. Therefore, although the raw output from the CNN classifier may adequately represent faults in synthetic data of simple structure and low noise, some post-processing steps are needed for the result to be useful on field data. Based on the traditional coherence attribute, Qi et al. (2017) introduced an image processing-based workflow to skeletonize faults. In this study, we regularize the raw output from a CNN fault detector with an image processing workflow built on Qi et al. (2017) to improve the fault images.

We use both a realistic synthetic data and field data to investigate the effectiveness of the proposed workflow. The synthetic data should ideally be a good approximation of field data and provide full control on the parameter set. We build our synthetic data based on the SEAM model (Fehler and Larner, 2008) by taking sub-volumes from the impedance model and inserting faults. After verifying the performance on the synthetic data, we then move on to field data acquired from the Great South Basin, offshore New Zealand, where extensive amount of faulting occurs. Results on both synthetic and field data show great potential of the proposed fault detection workflow which provides very clean fault images.

Proposed Workflow

The proposed workflow starts with a CNN classifier which is used to produce a raw image of faults. In this study, we adopt a 3D patch-based CNN model that classifies each seismic sample using samples within a 3D window. An example of the CNN architecture used in this study is provided in Figure 1. Basic patch-based CNN model consists of several convolutional layers, pooling (downsampling) layers, and fully-connected layers. Given a 3D patch of seismic amplitudes, a CNN model first automatically extracts several high-level abstractions of the image (similar to seismic attributes) using the convolutional and pooling layers, then classifies the extracted attributes using the fully- connected layers, which behave similar to a traditional multilayer perceptron network. The output from the network is then a single value representing the facies label of the seismic sample centered at the 3D patch. In this study, the label is binary, representing “fault” or “non-fault”.

Figure 1. Sketches of a 2D patch-based CNN architecture. In this demo case, each input data instance is a small 2D patch of seismic amplitude centered at the sample to be classified. The corresponding output is a class label representing the patch (in this case, fault), which is usually assigned to the center sample. Different types of layers are denoted in different colors, with layer types marked at their first appearance in the network. The size of the cuboids approximately represents the output size of each layer.

We then use a suite of image processing techniques to improve the quality of the fault images. First, we use a directional Laplacian of Gaussian (LoG) filter (Machado et al., 2016) to enhance lineaments that are of high angle from layering reflectors and suppress anomalies close to reflector dip, while calculating the dip, azimuth, and dip magnitude of the faults. Taking these data, we then use a skeletonization step, redistributing the fault anomalies within a fault damage zone to the most likely fault plane. We then do a thresholding to generate a binary image for faults. Optionally, if the result is still noisy, we can continue with a median filter to reduce the random noise and iteratively perform the directional LoG and skeletonization to achieve a desirable result. Figure 2 summarizes the regularization workflow.

Synthetic Test

We first test the proposed workflow on synthetic data built on the SEAM model. To make the model a good approximation of real field data, we select a portion in the SEAM model where stacked channels and turbidites exist. We then randomly insert faults in the impedance model and convolve with a 40Hz Ricker wavelet to generate seismic volumes. The parameters used in random generation of five reverse faults in the 3D volume are provided in Table 1. Figure 3a shows one line from the generated synthetic data with faults highlighted in red. In this model, we observe strong layer deformation with amplitude change along reflectors due to the turbidites in the model. Therefore, such synthetic data are in fact quite challenging for a fault detection algorithm, because of the existence of other types of discontinuities.

We randomly use 20% of the samples on the fault planes and approximately the same amount of non-fault samples to train the CNN model. The total number of training sample is about 350,000, which represents <1% of the total samples in the seismic volume. Figure 3b shows the raw output from the CNN fault detector on the same line shown in Figure 3a. We observe that instead of sticks, faults appear as a small zone. Also, as expected, there are some misclassifications where data are quite challenging. We then perform the regularization steps excluding the optional steps in Figure 2. Figure 3c shows the result after directional LoG filter and skeletonization. Notice that these two steps have cleaned up much of the noise, and the faults are now thinner and more continuous. Finally, we perform a thresholding to generate a fault map where faults are labeled as “1” and “0” for everywhere else (Figure 3d). Figure 4 shows the fault detection result on a less challenging line. We observe that the result on such line is nearly perfect.

Figure 2. The regularization workflow used to improve the fault images after CNN fault detection.

Fault attributeValues range
Dip angle (degree)-15 to 15
Strike angle (degree)-25 to 25
Displacement (m)25 to 75

Table 1. Parameter ranges used in generating faults in the synthetic model.

Field Data Test

We further verify the proposed workflow on field data from the Great South Basin, offshore New Zealand. The seismic data contain extensive faulting with complex geometry, as well as other types of coherence anomalies as shown in Figure 5. In this case, we manually picked training data on five seismic lines for regions representing fault and non-fault. An example line is given in Figure 6. As one may notice, although the training data consist very limited coverage in the whole volume, we try to include the most representative samples for the two classes. On the field data, we use the whole regularization workflow including the optional steps. Figure 7 gives the final output from the proposed workflow, and the result from using coherence in lieu of raw CNN output in the workflow. We observe that the result from CNN plus regularization gives clean fault planes with very limited noise from other types of discontinuities.

Conclusion

In this study, we introduce a fault detection workflow using both CNN-based classification and image processing regularization. We are able to train a CNN classifier to be sensitive to only faults, which greatly reduces the mixing between faults and other discontinuities in the produced faults images. To improve the resolution and further suppress non-fault features in the raw fault images, we then use an image processing-based regularization workflow to enhance the fault planes. The proposed workflow shows great potential on both challenging synthetic data and field data.

Acknowledgements

The authors thank Geophysical Insights for the permission to publish this work. We thank New Zealand Petroleum and Minerals for providing the Great South Basin seismic data to the public. The CNN fault detector used in this study is implemented in TensorFlow, an open source library from Google. The authors also thank Gary Jones at Geophysical Insights for valuable discussions on the SEAM model.

Figure 3. Line A from the synthetic data showing seismic amplitude with a) artificially created faults highlighted in red; b) raw output from CNN fault detector; c) CNN detected faults after directional LoG and skeletonization; and d) final fault after thresholding.

Figure 4. Line B from the synthetic data showing seismic amplitude co-rendered with a) randomly created faults highlighted in red and b) final result from the fault detection workflow, in which predicted faults are marked in red.

Figure 5. Coherence attribute along t = 1.492s. Coherence shows discontinuities not limited to faults, posting challenges to obtain only fault images.

Figure 6. A vertical slice from the field seismic amplitude data with manually picked regions for training the CNN fault detector. Green regions represent fault and red regions represent non-fault.

References

Araya-Polo, M., T. Dahlke, C. Frogner, C. Zhang, T. Poggio, and D. Hohl, 2017, Automated fault detection without seismic processing: The Leading Edge, 36, 208–214.

El-Sayed, M. A., Y. A. Estaitia, and M. A. Khafagy, 2013, Automated edge detection using convolutional neural network: International Journal of Advanced Computer Science and Applications, 4, 11–17.

Fehler, M., and K. Larner, 2008, SEG Advanced Modeling (SEAM). Phase I first year update: The Leading Edge, 27, 1006–1007.

Huang, L., X. Dong, and T. E. Clee, 2017, A scalable deep learning platform for identifying geologic features from seismic attributes: The Leading Edge, 36, 249–256.

Machado, G., A. Alali, B. Hutchinson, O. Olorunsola, and K. J. Marfurt, 2016, Display and enhancement of volumetric fault images: Interpretation, 4, 1, SB51–SB61.

Marfurt, K. J., V. Sudhaker, A. Gersztenkorn, K. D. Crawford, and S. E. Nissen, 1999, Coherency calculations in the presence of structural dip: Geophysics, 64, 104–111.

Qi, J., G. Machado, and K. Marfurt, 2017, A workflow to skeletonize faults and stratigraphic features: Geophysics, 82, no. 4, O57–O70.

Waldeland, A. U., and A. H. S. S. Solberg, 2017, Salt classification using deep learning: 79th Annual International Conference and Exhibition, EAGE, Extended Abstracts, Tu-B4-12.

Wu, X., and D. Hale, 2016, 3D seismic image processing for faults: Geophysics, 81, no. 2, IM1–IM11.

Xie, S., and Z. Tu, 2015, Holistically-nested edge detection: Proceedings of the IEEE International Conference on Computer Vision, 1395–1403.

Significant Advancements in Seismic Reservoir Characterization with Machine Learning

Significant Advancements in Seismic Reservoir Characterization with Machine Learning

By: Rocky Roden and Patricia Santogrossi
Published with permission: The First – SPE Norway Magazine
Volume 3 September 2017

The application of machine learning to classify seismic attributes at single sample resolution is producing results that reveal more reservoir characterization information than is available from traditional interpretation methods. Two consequences of applying machine learning with several appropriately chosen seismic attributes include the discrimination of thin beds that are below conventional seismic tuning and the identification of Direct Hydrocarbon Indicators (DHIs). These capabilities enable a higher resolution interpretation of reservoirs and stratigraphy. An explanation of the machine learning methodology and its application to thin beds and DHIs is described briefly in this paper.

 

Machine Learning Methodology

Taking advantage of today’s computing technology, visualization techniques, and an understanding of machine learning on seismic data, Self-Organizing Maps (SOMs) (Kohonen, 2001), efficiently distills multiple seismic attributes into classification and probability volumes (Smith and Taner, 2010). When applied on a multi-attribute seismic sample basis, SOM is a powerful nonlinear cluster analysis and pattern recognition machine learning approach that helps interpreters identify patterns in their data that can relate to inherent geologic characteristics and different aspects of their data. SOM analysis, which is an unsupervised neural network application, when properly applied has been able to reveal both thin beds and DHIs in appropriate geologic settings. Figure 1 illustrates a single seismic amplitude trace and seven different seismic attributes computed from the amplitude data. All of these traces are displayed in a wiggle-trace variable area format. This display represents 100 ms vertically and each horizontal scale line represents a sample (4 ms). Each of these attributes are at different scales and in some cases vastly different scales. It is evident from this Figure that each of the attributes measures a different component of the total acoustic energy at every sample. SOM identifies clusters where different combinations of attributes congregate to reveal significant information about the natural groupings that are difficult to view any other way. The self-organizing property of SOM identifies and classifies natural clusters.

The SOM machine learning process is graphically presented in Figure 2.  How large an area to select is dependent on the size of the geologic feature to be interpreted.  For thin beds and DHIs, usually, a relatively thin zone of 50-250 ms around the anomalies is selected over a reasonable areal extent to provide sufficient data points for the SOM analysis.  The selection of the seismic attributes is usually based on principal component analysis (PCA) and an interpreter’s knowledge of appropriate attributes for the area. Experience with SOM analysis has indicated that six to ten instantaneous seismic attributes are usually selected for thin beds and DHIs, depending on the geologic setting and data quality.  In Figure 2 ten attributes are employed and all the data points from every sample from these attributes in the zone to be analyzed are placed in attribute space where they are normalized to put on the same scale. The SOM process employs cooperative and competitive learning techniques to identify the natural patterns or clusters in the data. Each pattern is identified by a neuron that sorts through the data in attribute space during the SOM training process of self-organization. In Figure 2 after training is completed, 64 winning neurons have identified 64 patterns or clusters in attribute space with an 8X8 neuron network.  The SOM results are nonlinearly mapped back to a neuron topology map (2D colormap) where interpreters can select the winning neurons from the 2D colormap and identify in the 3D volume where the patterns and clusters occur for thin beds and DHIs.

 

wiggle trace seismic data

Figure 1. Wiggle-trace variable area display format of a 100 ms window of seismic data with the amplitude trace and seven associated traces of attributes. Each attribute trace is at a different scale and each horizontal scale line is separated by the sample interval of 4 ms. If all these traces were employed in a SOM analysis, each red circle along a timing line indicates samples that would be input as a multi-attribute sample.

SOM workflow for seismic interpretation

Figure 2. Display of SOM workflow where selected volume and data points from ten associated seismic attributes are input into Attribute Space. These data points are scaled and analyzed by the SOM process to identify 64 patterns by associated winning neurons. These neurons are nonlinearly mapped back to a 2D colormap where interpreters identify neurons and visually view the location of the patterns in the 3D survey.

 

In addition to the resultant classification volume, a probability volume is also generated which is a measure of the Euclidean distance from a data point to its associated winning neuron in attribute space (Roden et al., 2015). The winning neuron identifies a specific cluster or pattern.  It has been discovered that a low classification probability corresponds to areas that are quite anomalous as opposed to high probability zones that relate to regional and common events in the data.  Low probability anomalies identified by the SOM process are quite often associated with DHI characteristics.

 

Discriminating Thin Beds

The conventionally accepted definition of the tuning thickness (vertical resolution) is a bed that is ¼ wavelength in thickness, for which reflections from its upper and lower surfaces interfere and interference is constructive where the interface contrasts are of opposite polarity, often resulting in an exceptionally strong reflection (Sheriff, 2002). Several authors have described approaches to measure below tuning or thin beds usually employing various scaling techniques of amplitude or inversion data (MeckelandNath, 1977; Neidell and Poggiagliolmi, 1977; Schramm et al., 1977; Brown et al., 1986; and Connolly, 2007). However, these various techniques to determine thin beds have limitations and require assumptions that may not be met consistently (Simm, 2009). The application of SOM machine learning utilizing a multi-attribute classification has enabled the identification of thin beds and stratigraphy below tuning in a systematic and consistent manner as represented in the following case study.

The Eagle Ford Shale is a well-known unconventional resource play in Texas. Operators in this play must account for changing stratigraphy and facies to properly locate horizontal wells for optimum perforation intervals.  The Eagle Ford stratigraphy is often associated with thin beds and facies well below conventional seismic resolution that change both vertically and laterally. This Eagle Ford case study contains 216 mi² (560 km²) of enhanced 3D PSTM data processed at a 2 ms sample interval. Conventional vertical resolution (tuning thickness) is 100-150 feet (30-45 meters) depending on the location within the Eagle Ford unit. In this study, over 300 wells were available for correlation including 23 type logs, 249 horizontal borehole montages, 9 vertical calibration wells with tops, logs, and time-depth corrections. Also available were five cores for which X-ray diffraction and saturation information was available. Well information was incorporated to corroborate the SOM results.

SOM classification of seismic data

Figure 3. Resolution comparison between conventional seismic display and a Paradise® multi-attribute Self Organizing Map (SOM) classification: (a) Seismic amplitude profile through the 6 Well; and (b) the SOM results of the same profile identifying the Eagle Ford Group that comprises 26 sample based neuron clusters which are calibrated to facies and systems tracts. The 2D colormap displays the associated winning neuron cluster colors.

Ten instantaneous seismic attributes prominent in a Principal Component Analysis were selected for SOM. SOM training was conducted on a set of trial harvest lines and the successful line was then used to classify the entire survey. Figure 3a is a seismic amplitude line in color raster and wiggle-trace variable area formats across the location of Well 6 (V and 1H). The Figure shows the Austin Chalk-Eagle Ford Group-Buda stratigraphic interval represented by roughly 2.5 peak/trough cycles of a seismic trace. In the Eagle Ford, the amplitude appears continuous, yet any details are obscured because of the resolution limitations of the amplitude data where conventional tuning is 100-150 feet (30-45 meters). Figure 3b displays the equivalent line showing results of the SOM analysis. Sixty-four neurons were employed to identify 64 patterns in the data as seen on the associated 2D colormap. A seismic interval from 10 ms below the Buda to 100 ms above the Buda or near the top of the Austin Chalk was chosen for the SOM analysis. Shown clearly comparing Figures 3a and 3b is the resolution improvement provided by the SOM analysis over the seismic amplitude. The results reveal non-layer cake facies bands that include details in the Eagle Ford’s basal clay-rich shale, high resistivity and low resistivity Eagle Ford Shale objectives, the Eagle Ford ash, and the Upper Eagle Ford marl, which are overlain disconformably by the Austin Chalk (disconformity is a break in a sedimentary sequence that does not involve a difference in bedding angles). This interval of roughly 28 ms (or 14 samples) amounts to some 26 of the 64 SOM winning neurons to illuminate the various systems tracts within the Eagle Ford Group for this survey.

Adjacent to the SOM results at Well 6 are similar results at a nearby well. Figure 4a displays a zoomed-in vertical line display of the SOM results through Well 8(V) with the winning neurons identified. Figure 4b denotes the associated well log curves from well 8 and the correlative neuron associations. Winning neurons 63 and 64 are associated with the low resistivity Eagle Ford shale unit and neurons 53, 54, and 60 denote the high resistivity and more desirable Eagle Ford unit. The expanded display of the SOM results in Figure 4a denotes a low resistivity gold thin bed that is identified by a single neuron (#55) and is only one sample thick (2 ms). Shown here is clear evidence of consistent results between Wells 6 and 8 that lends itself to stratigraphic facies interpretation.

Calibrating SOM to well logs

Figure 4. View of SOM results correlated with Well 8 logs: (a) Expanded view of SOM profile through Well 8; and (b) Well 8 logs with Eagle Ford units correlated with the SOM results of (a). Note that the resolution is down to the sample level of 10-12 feet and is illustrated by winning neuron 55 in (a). The dashed white line in (a) represents the top of the Eagle Ford and base of the Austin Chalk.

Over this survey area, 16 different winning neurons represent the various facies present in the Eagle Ford Shale over a 14 ms window (70-84 feet/21-26 meters). The facies of the entire Eagle Ford Group which includes the Basal Clay shale, Eagle Ford Shale, and Eagle Ford Marl, are defined by 26 different winning neurons over 28 ms (210-252 feet/64-77 meters). Individual facies units are as thin as one sample interval of 2 ms (10-12 feet/3-4 meters). These results of a single SOM classification are corroborated at multiple wells across the survey area.

 

Revealing Direct Hydrocarbon Indicators (DHIs)

The accurate interpretation of seismic DHI characteristics has proven to significantly improve the drilling success rates in the appropriate geologic setting where there is also adequate seismic data quality (Roden et al., 2012; Rudolph and Goulding, 2017). Specifically, DHIs are anomalies due to the presence of hydrocarbons induced by changes in rock physics properties (P and S wave velocities, and density). Typically, anomalies stand out as the difference in a hydrocarbon-filled reservoir in relation to the encasing rock or the brine portion of the reservoir. DHI characteristics are usually associated with anomalous seismic responses in a trapping configuration, such as structural traps, stratigraphic traps, or a combination of both. These include bright spots, flat spots, amplitude conformance to structure, etc. DHI anomalies are often compared to models, similar events, background trends, proven productive anomalies, and geologic features. DHI indicators can also be located below presumed trapped hydrocarbons where shadow zones or velocity pull-down effects may be present. These DHI effects can even be present and dispersed in the sediment column in the form of gas chimneys or clouds.

As described above there are numerous DHI characteristics and all of which should be evaluated in a consistent and systematic approach for any prospect or project. Forrest et al. (2010) and Roden et al. (2012) have identified the top four DHI characteristics, as related to commercially successful wells in a Class 3 AVO setting, based on an industry-wide database of almost 300 wells. These DHI characteristics include:

  1. Anomaly conformance to structure
  2. Phase or character change at the downdip edge of the anomaly
  3. Anomaly consistency in the mapped target area
  4. Flat spots

SOM low probability anomaly

Figure 5. From the top of the producing reservoir: a) time structure map in contours with an amplitude overlay in color and b) SOM classification with low probability less than 1% denoted by white areas. The yellow line in b) represents the downdip edge of the high amplitude zone picked from a).

These DHI characteristics will be identified in the following case study by a multi-attribute SOM analysis. The case study is an offshore oil/gas field in 470 feet (145 meters) of water on the Louisiana continental shelf of the Gulf of Mexico. The field has two producing wells that were drilled on the upthrown side of a normal fault and into an amplitude anomaly. The normally pressured reservoir is approximately 100 feet (30 meters) thick and contains oil and gas. The hydrocarbon filled sandstone reservoir has low impedance compared to the encasing shales, indicative of a Class 3 AVO environment. The SOM analyzed a 170 ms window surrounding the reservoir. Applying the (SOM) multi-attribute analysis, a group of eight seismic attributes was selected based on Principal Component Analysis that would best expose Direct Hydrocarbon Indicators (DHIs). A neuron network of 5X5 (25 neurons) was employed. Figure 5a displays a time structure map as denoted by the contours with an amplitude overlay (color) from the mapped top of the reservoir in this field. The horizon at the top of the reservoir was picked on a trough (low impedance) on zero phase seismic data (SEG normal polarity).
Figure 5a indicates there is a relatively good amplitude conformance to structure based on the amplitude as noted by the general agreement of the time contour and the red/green amplitude break (see color bar insert). Figure 5b is a display of classification probability from the SOM analysis at the top of the reservoir at the same scale as Figure 5a. This indicates that the top of the reservoir exhibits an anomalous response from the SOM analysis. Ordinary classifications such as those of green and yellow-greens are shown around the reservoir (see colormap insert). However, within the reservoir and in several other areas, anomalous classification of low probability below 1% are colored white. In comparing Figure 5a and 5b it is apparent that the low probability area corresponds closely to the amplitude conformance to structure as denoted by the yellow outline in Figure 5b. This confirms the identification of the productive area with low probability and proves the efficacy of this SOM approach. The consistency of the low probability SOM response in the field is another positive DHI indicator. In fact, the probabilities as low as .01% still produce a consistent response over the field indicating how significant evaluating low probability anomalies is critical in the interpretation of DHI characteristics.

gas oil and oil water contacts in a SOM

Figure 6. North-south vertical profile 9411 through the middle of the field: a) stacked seismic amplitude display with the field location marked, b) SOM classification with 25 neurons (5X5) indicated by the 2D colormap over a 170 ms window, and c) three neurons highlighting the reservoir above the oil/water and gas/oil contacts and the hydrocarbon contacts (flat spots) as marked by winning neurons 15, 20, and 25. The expanded insets in the right column denote the details from the SOM results at the downdip edge of the field (see dashed black boxes on left).

This field contains an oil phase with a gas cap and before drilling, there were hints of possible flat spots suggesting hydrocarbon contacts on the seismic data, but the evidence was inconsistent and not definitive. Figure 6 displays a north-south vertical inline seismic profile through the middle of the field with its location denoted in Figure 5. Figure 6a exhibits the initial stacked amplitude data with the location of the field marked. Figure 6b denotes the SOM analysis results of this same vertical inline which incorporates the eight instantaneous attributes listed with the 5X5 neuron matrix in Figure 5. The associated 2D colormap in Figure 6b denotes the 25 natural patterns or clusters identified from the SOM process (see colormap insert). It is apparent in Figure 6b that the reservoir and portions of both the gas/oil contact and the oil/water contact are easily identified as opposed to the conventional seismic data shown in Figure 6a. This is more easily seen in Figure 6c where the 2D colormap indicates that the neurons highlighted in gray (winning neurons 20 and 25) are defining the hydrocarbon-bearing portions of the reservoir above the hydrocarbon contacts and the flat spots interpreted as hydrocarbon contacts are designated by the rust-colored winning neuron 15. The location of the reservoir and hydrocarbon contacts are corroborated by well control (not shown). Note that the southern edge of the reservoir is revealed in the enlargements in the column on the right (from the dashed black box on left). A character change at the downdip edge of the anomaly where the oil contact thins out is easily identified compared to the line of amplitude change. Downdip of the field is another undrilled anomaly defined by the SOM analysis that exhibits similar DHI characteristics identified by the same neurons.

 

Conclusions

A seismic multi-attribute analysis utilizing Self-Organizing-Maps is a machine learning approach that distills information from numerous attributes on a sample-by-sample basis to provide a more accurate assessment of thin beds and DHI characteristics than conventional methods. We have shown in these cases that the results readily correlate to conventional well log data. The SOM classification process takes advantage of natural patterns in multiple seismic attributes space that is not restricted to the resolution limits of conventional amplitude data. This process enables interpreters to produce higher resolution interpretations of reservoirs and stratigraphy. Another advantage of a SOM analysis is the generation of classification probability where low probability anomalies are often associated with DHIs. SOM analyses in appropriate geologic settings can improve confidence in interpreting DHI characteristics and more clearly define reservoir edges and thin bed components.

 

References

Brown, A. R., R. M. Wright, K. D. Burkart, W. L. Abriel, and R. G. McBeath, 1986, Tuning effects, lithological effects and depositional effects in the seismic response of gas reservoirsGeophysical Prospecting, 32, 623-647.

Connolly, P., 2007, A simple, robust algorithm for seismic net pay estimationThe Leading Edge, 26, 1278-1282.

Forrest, M., R. Roden, and R. Holeywell, 2010, Risking seismic amplitude anomaly prospects based on database trendsThe Leading Edge, 5, 936-940.

Kohonen, T., 2001, Self-Organizing Maps: third extended editionSpringer Series in Information Services, Vol. 30.

Meckel, L. D., and A. K. Nath, 1977, Geologic consideration for stratigraphic modelling and interpretationIn: Payton, C. E. (Ed.) Seismic Stratigraphy- Applications to hydrocarbon ExplorationAAPG Memoir 26, 417-438.

Neidell, N. S., and E. Poggiagliolmi, 1977, Stratigraphic modeling and interpretation-Geophysical principles and techniques. In: Payton, C. E. (Ed.) Seismic Stratigraphy-Applications to hydrocarbon Exploration. AAPG Memoir 26, 389-416.

Roden, R., M. Forrest, and R. Holeywell, 2012, Relating seismic interpretation to reserve/resource calculations: Insights from a DHI consortium: The Leading Edge, 9, 1066-1074.

Roden, R., T. Smith, and D. Sacrey, 2015, Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing mapsInterpretation, 3, SAE59-SAE83.

Rudolph, K. W., and F. J. Goulding, 2017, Benchmarking exploration predictions and performance using 20+ yr of drilling results: One company’s experience: AAPG Bulletin, 101, 161-176.

Schramm Jr., M. W., E. V. Dedman, and J. P. Lindsey, 1977, Practical stratigraphic modeling and interpretation. In: Payton, C. E. (Ed.) Seismic Stratigraphy-Applications to hydrocarbon ExplorationAAPG Memoir 26, 477-502.

Sheriff, R. E., 2002, Encyclopedic dictionary of applied geophysics, 4th ed.: SEG.

Simm, R. W., 2009, Simple net pay estimation from seismic: a modelling study: First Break, 27, 45-53.

Smith, T. and M. T. Taner, 2010, Natural clusters in multi-attribute seismics found with self-organizing maps: Extended Abstracts, Robinson-Treitel Spring Symposium by GSH/SEG, March 10-11, 2010, Houston, Tx.

About the Authors

Rocky Roden, Consulting Geophysicist, Geophysical Insights

Rocky R. Roden has extensive knowledge of modern geoscience technical approaches (past Chairman-The Leading Edge Editorial Board). As former Chief Geophysicist and Director of Applied Technology for Repsol-YPF, his role comprised advising corporate officers, geoscientists, and managers on interpretation, strategy and technical analysis for exploration and development in offices in the U.S., Argentina, Spain, Egypt, Bolivia, Ecuador, Peru, Brazil, Venezuela, Malaysia, and Indonesia. He has been involved in the technical and economic evaluation of Gulf of Mexico lease sales, farmouts worldwide, and bid rounds in South America, Europe, and the Far East. Previous work experience includes exploration and development at Maxus Energy, Pogo Producing, Decca Survey, and Texaco. He holds a B.S. in Oceanographic Technology-Geology from Lamar University and a M.S. in Geological and Geophysical Oceanography from Texas A&M University.

Patricia Santogrossi, Sr. Geoscientist, Geophysical Insights

Patricia Santogrossi is a Consultant to Geophysical Insights, producer of the Paradise multi-attribute analysis software platform. Formerly, she was a Leading Reservoir Geoscientist and Non-operated Projects Manager with Statoil USA E & P. In this role Ms. Santogrossi was engaged for nearly nine years in Gulf of Mexico business development, corporate integration, prospect maturation, and multiple appraisal projects in the deep and ultra-deepwater Gulf of Mexico. Ms. Santogrossi has previously worked with domestic and international Shell Companies, Marathon Oil Company, and Arco/Vastar Resources in research, exploration, leasehold and field appraisal as well as staff development. She has also been Chief Geologist for Chroma Energy, who possessed proprietary 3D voxel multi-attribute visualization technology, and for Knowledge Reservoir, a reservoir characterization and simulation firm that specialized in Deepwater project evaluations. She is a longtime member of SEPM, AAPG, GCSSEPM, HGS and SEG and has held various elected and appointed positions in many industry organizations. Ms. Santogrossi holds an M.S. in Geology from the University of Illinois, Champaign-Urbana.

 

 

 

Geobody Interpretation Through Multi-Attribute Surveys, Natural Clusters and Machine Learning

By Thomas A. Smith 
June 2017

Geobody interpretation through multi-attribute surveys, natural clusters and machine learning

Summary

Multi-attribute seismic samples (even as entire attribute surveys), Principal Component Analysis (PCA), attribute selection lists, and natural clusters in attribute space are candidate inputs to machine learning engines that can operate on these data to train neural network topologies and generate autopicked geobodies. This paper sets out a unified mathematical framework for the process from seismic samples to geobodies.  SOM is discussed in the context of inversion as a dimensionality-reducing classifier to deliver a winning neuron set.  PCA is a means to more clearly illuminate features of a particular class of geologic geobodies.  These principles are demonstrated with geobody autopicking below conventional thin bed resolution on a standard wedge model.

Introduction

Seismic attributes are now an integral component of nearly every 3D seismic interpretation.  Early development in seismic attributes is traced to Taner and Sheriff (1977).  Attributes have a variety of purposes for both general exploration and reservoir characterization, as laid out clearly by Chopra and Marfurt (2007).  Taner (2003) summarizes attribute mathematics with a discussion of usage.

Self-Organizing Maps (SOM) are a type of unsupervised neural networks that self-train in the sense that they obtain information directly from the data.  The SOM neural network is completely self-taught, which is in contrast to the perceptron and its various cousins undergo supervised training.  The winning neuron set that results from training then classifies the training samples to test itself by finding the nearest neuron to each training sample (winning neuron).  In addition, other data may be classified as well.  First discovered by Kohonen (1984), then advanced and expanded by its success in a number of areas (Kohonen, 2001; Laaksonen, 2011), SOM has become a part of several established neural network textbooks, namely Haykin (2009) and Dutta, Hart and Stork (2001).  Although the style of SOM discussed here has been used commercially for several years, only recently have results on conventional DHI plays been published (Roden, Smith and Sacrey, 2015).

Three Spaces

The concept of framing seismic attributes as multi-attribute seismic samples for SOM training and classification was presented by Taner, Treitel, and Smith (2009) in an SEG Workshop.  In that presentation, survey data and their computed attributes reside in survey space.  The neural network resides in neuron topology space.  These two meet in attribute space where neurons hunt for natural clusters and learn their characteristics.

Results were shown for 3D surveys over the venerable Stratton Field and a Gulf of Mexico salt dome.  The Stratton Field SOM results clearly demonstrated that there are continuous geobody events in the weak reflectivity zone between C38 and F11 events, some of which are well below seismic tuning thickness, that could be tied to conventional reflections and which correlated with wireline logs at the wells.  Studies of SOM machine learning of seismic models were presented by Smith and Taner (2010).  They showed how winning neurons distribute themselves in attribute space in proportion to the density of multi-attribute samples.  Finally, interpretation of SOM salt dome results found a low probability zone where multi-attribute samples of poor fit correlated with an apparent salt seal and DHI down-dip conformance (Smith and Treitel, 2010).

Survey Space to Attribute Space:

Ordinary seismic samples of amplitude traces in a 3D survey may be described as an ordered  set .  A multi-attribute survey is a “Super 3D Survey” constructed by combining a number of attribute surveys with the amplitude survey.  This adds another dimension to the set and another subscript, so the new set of samples including the additional attributes is .  These data may be thought of as separate surveys or equivalently separate samples within one survey.  Within a single survey, each sample is a multi-attribute vector.  This reduces the subscript by one count so the set of multi-attribute vectors  .

Next, a two-way mapping function may be defined that references the location of any sample in the 3D survey by single and triplet indices  Now the three survey coordinates may be gathered into a single index so the multi-attribute vector samples are also an unordered set in attribute space  The index map is a way to find a sample a sample in attribute space from survey space and vice versa.

Multi-attribute sample and set in attribute space: 

A multi-attribute seismic sample is a column vector in an ordered set of three subscripts c,d,e representing sample index, trace index, and line index. Survey bins refer to indices d and e.  These samples may also be organized into an unordered set with subscript i.  They are members of an -dimensional real space.  The attribute data are normalized so in fact multi-attribute samples reside in scaled attribute space.

Natural clusters in attribute space: 

Just as there are reflecting horizons in survey space, there must be clusters of coherent energy in attribute space.  Random samples, which carry no information, are uniformly distributed in attribute space just as in survey space.  The set  of natural clusters in attribute space is unordered and contains m  members.  Here, the brackets [1, M]  indicate an index range.  The natural clusters may reside anywhere in attribute space, but attribute space is filled with multi-attribute samples, only some of which are meaningful natural clusters.  Natural clusters may be big or small, tightly packed or diffuse.  The rest of the samples are scattered throughout F-space.  Natural clusters are discovered in attribute space with learning machines imbued with simple training rules and aided by properties of their neural networks.

A single natural cluster: 

A natural cluster may have elements in it.  Every natural cluster is expected to have a different number of multi-attribute samples associated with it.  Each element is taken from the pool of the set of all multi-attribute samples   Every natural cluster may have a different number of multi-attribute samples associated with it so for any natural cluster,  then N(m).  Every natural cluster has its own unique properties described by the subset of samples  that are associated with it.  Some sample subsets associated with a winning neuron are small (“not so popular”) and some subsets are large (“very popular”).  The distribution of Euclidean distances may be tight (“packed”) or loose (“diffuse”).

Geobody sample and geobody set in survey space: 

For this presentation, a geobody G_b is defined as a contiguous region in survey space composed of elements which are identified by members g.  The members of a geobody are an ordered set  which registers with those coordinates of members of the multi-attribute seismic survey .

A geobody member is just an identification number (id), an integer .  Although the 3D seismic survey is a fully populated “brick” with members ,  the geobody members  register at certain contiguous locations, but not all of them.  The geobody  is an amorphous, but contiguous, “blob” within the “brick” of the 3D survey.  The coordinates of the geobody blob in the earth are  where  By this, all the multi-attribute samples in the geobody may be found, given the id and three survey coordinates of a seed point.

A single geobody in survey space

Each geobody  is a set of  N geobody  members with the same id.  That is, there are N members in , so N(b).  The geobody members for this geobody are taken from the pool of all geobody samples, the set  Some geobodies are small and others large.  Some are tabular, some lenticular, some channels, faults, columns, etc.  So how are geobodies and natural clusters related?

A geobody is not a natural cluster

This expression is short but sweet.  It says a lot.  On the left is the set of all B geobodies.  On the right is the set of M natural clusters.  The expression says that these two sets aren’t the same.  On the left, the geobody members are id numbers  These are in survey space.  On the right, the natural clusters  These are in attribute space.  What this means is that geobodies are not directly revealed by natural clusters.  So, what is missing?

Interpretation is conducted in survey space.  Machine learning is conducted in attribute space.  Someone has to pick the list of attributes.  The attributes must be tailored to the geological question at hand.  And a good geological question is always the best starting point for any interpretation.

A natural cluster is an imaged geobody

Here, a natural cluster C_m is defined as an unorganized set of two kinds of objects: a function I of a set of geobodies G_i and random noise N.  The number of geobodies is I and unspecified.  The function  is an illumination function which places the geobodies in  The illumination function is defined by the choice of attributes.  This is the attribute selection list.  The number of geobodies in a natural cluster C_m is zero or more, 0<i<I.  The geobodies are distributed throughout the 3D survey.

The natural cluster concentrates geobodies of similar illumination properties.  If there are no geobodies or there is no illumination with a particular attribute selection list,  , so the set is only noise.  The attribute selection list is a critically import part of multi-attribute seismic interpretation.  The wrong attribute list may not illuminate any geobodies at all.

Geobody inversion from a math perspective

Multi-attribute seismic interpretation proceeds from the preceding equation in three parts.  First, as part of an inversion process, a natural cluster   is statistically estimated by a machine learning classifier such as SOM  with a neural network topology.  See Chopra, Castagna and Potniaguie (2006) for a contrasting inversion methodology.  Secondly, SOM employs a simple training rule that a neuron nearest a selected training sample is declared the winner and the winning neuron advances toward the sample a small amount.  Neurons are trained by attraction to samples.  One complete pass through the training samples is called an epoch.  Other machine learning algorithm have other training rules to adapt to data.  Finally, SOM has a dimensionality reducing feature because information contained in natural clusters is transferred (imperfectly) to the winning neuron set in the finalized neural network topology through cooperative learning.  Neurons in winning neuron neighborhood topology move along with the winning neuron in attribute space.  SOM training is also dynamic in that the size of the neighborhood decreases with each training time step so that eventually the neighborhood shrinks so that all subsequent training steps are competitive.

Because  is a statistical estimate, let it be called the statistical estimate of the “signal” part of .  The true geobody is independent of an illumination function.  The dimensionality reduction   associated with multi-attribute interpretation has a purpose of geobody recognition through identification, dimensionality reduction and classification.  In fact, in the chain of steps there is a mapping and un-mapping process with no guarantee that the geobody will be recovered: 

However, the image function   may be inappropriate to illuminate the geobody in F-space because of a poor choice of attributes.  So at best, the geobodies is illuminated by an imperfect set of attributes and detected by a classifier that is primitive.  The results often must be combined, edited and packaged into useful, interpreted geobody units, ready to be incorporated into an evolving geomodel on which the interpretation will rest.

Attribute Space Illumination

One fundamental aspect of machine learning is dimensionality reduction from attribute space because its dimensions are usually beyond our grasp.  The approach taken here is from the perspective of manifolds which are defined as spaces with the property of “mapability” where Euclidean coordinates may be safely employed within any local neighborhood (Haykin, 2009, p.437-442).

The manifold assumption is important because SOM learning is routinely conducted on multi-attribute samples in attribute space using Euclidean distances to move neurons during training.  One of the first concerns of dimensionality reduction is the potential to lose details in natural clusters.  In practice, it has been found that halving the original amplitude sample interval is advantageous, but further downsampling has not proven to be beneficial.  Infilling a natural cluster allows neurons during competitive training to adapt to subtle details that might be missed in the original data.

Curse of Dimensionality

The Curse of Dimensionality (Haykin, 2009) is, in fact, many curses.  One problem is that uniformly sampled space increases dramatically with increasing dimensionality.  This has implications when gathering training samples for a neural network.  For example, cutting a unit length bar (1-D) with a sample interval of .01 results in 100 samples.  Dividing a unit length hypercube in 10-D with a similar sample interval results in 1020 samples (1010 x 102).  If the nature of attribute space requires uniform sampling across a broad numerical range, then a large number of attributes may not be practical.  However, uniform sampling is not an issue here because the objective is to locate and detail features of natural clusters.

Also, not all attributes are important.  In the hunt for natural clusters, PCA (Haykin, 2009) is often a valuable tool to assess the relative merits of each attribute in a SOM attribute selection list.  Depending on geologic objectives, several dominant attributes may be picked from the first, second or even third principal eigenvectors or may pick all attributes from one principle eigenvector.

Geobody inversion from an interpretation perspective

Multi-attribute seismic interpretation is finding geobodies in survey space aided by machine learning tools that hunt for natural clusters in attribute space.  The interpreter’s critical role in this process is the following:

  • Choose questions that carry exploration toward meaningful conclusions.
  • Be creative with seismic attributes so as to effectively address illumination of geologic geobodies.
  • Pick attribute selection lists with the assistance of PCA.
  • Review the results of machine learning which may identify interesting geobodies  in natural clusters autopicked by SOM.
  • Look through the noise to edit and build geobodies  with a workbench of visualization displays and a variety of statistical decision-making tools.
  • Construct geomodels by combining autopicked geobodies which in turn allow predictions on where to make better drilling decisions.

The Geomodel

After classification, picking geobodies from their winning neurons starts by filling an empty geomodel .  Natural clusters are consolidators of geobodies with common properties in attribute space so M < B.  In fact, it is often found that M << B .  That is, geobodies “stack” in attribute space.  Seismic data is noisy.  Natural clusters are consequentially statistical.  Not every sample g classified by a winning neuron is important although SOM classifies every sample. Samples that are a poor fit are probably noise.  Construction of a sensible geomodel depends on answering well thought out geological questions and phrased by selection of appropriate attribute selection lists.

Working below classic seismic tuning thickness

Classical seismic tuning thickness is λ/4.  Combining vertical incidence layer thickness  with  λ=V/f leads to a critical layer thickness  Resolution below classical seismic tuning thickness has been demonstrated with multi-attribute seismic samples and a machine learning classifier operating on those samples in scaled attribute space (Roden, et. al., 2015). High-quality natural clusters in attribute space imply tight, dense balls (low entropy, high density).  SOM training and classification of a classical wedge model at three noise levels is shown in Figures 1 and 2 which show tracking well below tuning thickness.

Seismic Processing: Processing the survey at a fine sample interval is preferred over resampling the final survey to a fine sample interval. Highest S/N ratio is always preferred. Preprocessing: Fine sample interval of base survey is preferred to raising the density of natural clusters and then computing attributes, but do not compute attributes and then resample because some attributes are not continuous functions. Derive all attributes from a single base survey in order to avoid misties. Attribute Selection List: Prefer attributes that address the specific properties of an intended geologic geobody. Working below tuning, prefer instantaneous attributes over attributes requiring spatial sampling.  Thin bed results on 3D surveys in the Eagle Ford Shale Facies of South Texas and in the Alibel horizon of the Middle Frio Onshore Texas and Group corroborated with extensive well control to verify consistent results for more accurate mapping of facies below tuning without usual traditional frequency assumptions (Roden, Smith, Santogrossi and Sacrey, personal communication, 2017).

Conclusion

There is a firm mathematical basis for a unified treatment of multi-attribute seismic samples, natural clusters, geobodies and machine learning classifiers such as SOM.  Interpretation of multi-attribute seismic data is showing great promise, having demonstrated resolution well below conventional seismic thin bed resolution due to high-quality natural clusters in attribute space which have been detected by a robust classifier such as SOM.

Acknowledgments

I am thankful to have worked with two great geoscientists, Tury Taner and Sven Treitel during the genesis of these ideas.  I am also grateful to work with an inspired and inspiring team of coworkers who are equally committed to excellence.  In particular, Rocky Roden and Deborah Sacrey are longstanding associates with a shared curiosity to understand things and colleagues of a hunter’s spirit.

Figure 1: Wedge models for three noise levels trained and classified by SOM with attribute list of amplitude and Hilbert transform (not shown) on 8 x 8 hexagonal neuron topology. Upper displays are amplitude. Middle displays are SOM classifications with a smooth color map. Lower displays are SOM classifications with a random color map. The rightmost vertical column is an enlargement of wedge model tips at highest noise level.  Multi-attribute classification samples are clearly tracking well below tuning thickness which is left of the center in the right column displays.

Figure 2: Attribute space for three wedge models with horizontal axis of amplitude and vertical axis of Hilbert transform. Upper displays are multi-attribute samples before SOM training and lower displays after training and samples classified by winning neurons in lower left with smooth color map.  Upper right is an enlargement of tip of third noise level wedge model from Figure 1 where below-tuning bed thickness is right of the thick vertical black line.

References

Chopra, S. J. Castagna and O. Potniaguine, 2006, Thin-bed reflectivity inversion, Extended abstracts, SEG Annual Meeting, New Orleans.

Chopra, S. and K.J. Marfurt, 2007, Seismic attributes for prospect identification and reservoir characterization, Geophysical Developments No. 11, SEG.

Dutta, R.O., P.E. Hart and D.G. Stork, 2001, Pattern Classification, 2nd ed.: Wiley.

Haykin, S., 2009, Neural networks and learning machines, 3rd ed.: Pearson.

Kohonen, T., 1984, Self-organization and associative memory, pp 125-245. Springer-Verlag. Berlin.

Kohonen, T., 2001, Self-organizing maps: Third extended addition, Springer, Series in Information Services.

Laaksonen, J. and T. Honkela, 2011, Advances in self-organizing maps, 8th International Workshop, WSOM 2011 Espoo, Finland, Springer.

Ma, Y. and Y. Fu, 2012, Manifold Learning Theory and Applications, CRC Press, Boca Raton.

Roden, R., T. Smith and D. Sacrey, 2015, Geologic pattern recognition from seismic attributes, principal component analysis and self-organizing maps, Interpretation, SEG, November 2015, SAE59-83.

Smith, T., and M.T. Taner, 2010, Natural clusters in multi-attribute seismics found with self-organizing maps: Source and signal  processing section paper 5: Presented at Robinson-Treitel Spring Symposium by GSH/SEG, Extended Abstracts.

Smith, T. and S. Treitel, 2010, Self-organizing artificial neural nets for automatic anomaly identification, Expanded abstracts, SEG Annual Convention, Denver.

Taner, M.T., 2003, Attributes revisited, http://www.rocksolidimages.com/attributes-revisited/, accessed 22 March 2017.

Taner, M.T., and R.E. Sheriff, 1977, Application of amplitude, frequency, and other attributes, to stratigraphic and hydrocarbon  determination, in C.E. Payton, ed., Applications to hydrocarbon exploration: AAPG Memoir 26, 301–327.

Taner, M.T., S. Treitel, and T. Smith, 2009, Self-organizing maps of multi-attribute 3D seismic reflection surveys, Presented at the 79th International SEG Convention, SEG 2009 Workshop on “What’s New in Seismic Interpretation,” Paper no. 6.

ChingWen Chen, seismic interpreterTHOMAS A. SMITH is president and chief executive officer of Geophysical Insights, which he founded in 2008 to develop machine learning processes for multiattribute seismic analysis. Smith founded Seismic Micro-Technology in 1984, focused on personal computer-based seismic interpretation. He began his career in 1971 as a processing geophysicist at Chevron Geophysical. Smith is a recipient of the Society of Exploration Geophysicists’ Enterprise Award, Iowa State University’s Distinguished Alumni Award and the University of Houston’s Distinguished Alumni Award for Natural Sciences and Mathematics. He holds a B.S. and an M.S. in geology from Iowa State, and a Ph.D. in geophysics from the University of Houston.
  

Interpretation of DHI Characteristics with Machine Learning

Interpretation of DHI Characteristics with Machine Learning

By: Rocky Roden and ChingWen Chen, Ph.D.
Published with permission: First Break
Volume 35, May 2017

Introduction

In conventional geological settings, oil companies routinely evaluate prospects for their drilling portfolio where the process of interpreting seismic amplitude anomalies as Direct Hydrocarbon Indicators (DHIs) plays an important role. DHIs are an acoustic response owing to the presence of hydrocarbons and can have
a significant impact on prospect risking and determining well locations (Roden et al., 2005; Fahmy 2006; Forrest et al., 2010; Roden et al., 2012; Rudolph and Goulding, 2017). DHI anomalies are caused by changes in rock physics properties (P and S wave velocities, and density) typically of the hydrocarbon-filled
reservoir in relation to the encasing rock or the brine portion of the reservoir. Examples of DHIs include bright spots, flat spots, character/phase change at a projected oil or gas/water contact, amplitude conformance to structure, and an appropriate amplitude variation with offset on gathers. Many uncertainties should be considered and analyzed in the process of assigning a probability of success and resource estimate range before including a seismic amplitude anomaly prospect in an oil company’s prospect portfolio (Roden et al., 2012).

Seismic amplitude anomalies that are DHIs have played a major role in oil and gas exploration since the early 1970s (Hilterman, 2001). The technology and methods to identify and risk seismic amplitude anomalies have advanced considerably over the years, especially with the use of AVO (Amplitude vs. Offset) and improved acquisition and processing seismic technology (Roden et al., 2014). The proper evaluation of seismic direct hydrocarbon indicators for appropriate geologic settings has proven to have a significant impact on risking prospects. Rudolph and Goulding (2017) indicate from an ExxonMobil database of prospects that DHI-based prospects had over twice the success rate of non-DHI prospects on both a geologic and economic basis. In an industry-wide database of DHI prospects from around the world, Roden et al. (2012) indicate that when a prospect has a >20% DHI Index, a measure of the risk associated with DHI characteristics, almost all the wells were successful. Even with the use of advanced seismic technology and well-equipped interpretation workstations, the interpretation of DHI characteristics is not always easy or straightforward.

A key technology employed in evaluating potential DHI features is seismic attributes. Seismic attributes are any measurable property of seismic data including stacked or prestack data. Seismic attributes can be computed on a trace, multiple traces, on an entire volume, over isolated windows, on a horizon, and in either
time or depth. There are hundreds of seismic attributes generated in our industry (Brown, 2004; Chen and Sidney, 1997; Chopra and Marfurt, 2007; Taner, 2003) and can be generally categorized as instantaneous, geometric, AVO, seismic inversion, and spectral decomposition attributes. The instantaneous, AVO, and inversion attributes are typically utilized to highlight and identify DHI features. For example, amplitude envelope, average energy, and sweetness are good instantaneous attributes to display how amplitudes stand out above the background, potentially identifying a bright spot and a potential hydrocarbon accumulation. AVO attributes such as intercept times gradient, fluid factor, Lambda/Mu/Rho and far offset-minus near offset-times the far offset can help to identify hydrocarbon-bearing reservoirs (Roden et al., 2014). However, not all amplitude anomalies are DHIs and interpreting numerous seismic attributes can be complicated and at times confusing. In addition, it is almost impossible for geoscientists to understand how numerous seismic attributes (>3) interrelate.

Over the last few years, machine learning has evolved to help interpreters handle numerous and large volumes of data (e.g. seismic attributes) and help to understand how these different types of data relate to each other. Machine learning uses computer algorithms that iteratively learn from the data and independently adapt to produce reliable, repeatable results. We incorporate a machine learning workflow where principal component analysis (PCA) and self-organizing maps (SOM) are employed to analyze combinations of seismic attributes for meaningful patterns that correspond to direct hydrocarbon indicators. A machine learning multi-attribute approach with the proper input parameters can help interpreters to more efficiently and accurately evaluate DHIs and help reduce risk in prospects and projects.

Interpreting DHIs

Important DHI Characteristics

Table 1 Most important DHI characteristics for AVO classes 2 and 3 as determined by Forrest et al. (2010) and Roden et al. (2012)

DHI characteristics are usually associated with anomalous seismic responses in a trapping configuration: structural traps, stratigraphic traps, or a combination of both. These include bright spots, flat spots, amplitude conformance to structure, etc. DHI anomalies are also compared to other features such as models, similar events, background trends, proven productive anomalies, and geologic features. DHI indicators can also be located below presumed trapped hydrocarbons where shadow zones or velocity pull-down effects may be present. DHI effects can even be present dispersed in the sediment column in the form of gas chimneys or clouds. Forrest et al. (2010) and Roden et al. (2012) have documented the most important DHI characteristics based on well success rates in an industry-wide database of DHI prospects. Other than the amplitude strength above background (bright spots), Table 1 lists these DHI characteristics by AVO classes 2 and 3. These two AVO classes (Rutherford and Williams, 1989) relate to the amplitude with offset response from the top of gas sands which represent the specific geologic settings where most DHI characteristics are found. Therefore, the application of machine learning employing seismic multi-attribute analysis may help to clearly define DHI characteristics and assist the interpreter in making a more accurate assessment of prospect risk.

Class 3 DHI Characteristics

Table 2 Most important Class 3 DHI characteristics as denoted by Forrest et al. (2010) and Roden et al. (2012) and a designation of typical instantaneous attributes that identify these characteristics. Not all instantaneous attributes by themselves are conducive to identifying the top DHI characteristics.

Multi-attribute machine learning workflow

With the goal of identifying DHI characteristics, an interpreter must determine the specific attributes to employ in a machine learning workflow. A geoscientist can select appropriate attributes based on their previous knowledge and experience to define DHIs in a specific play or trend. Table 2 lists several common instantaneous attributes and the associated stacked seismic data DHI characteristics they tend to identify. These relationships are of course subjective and depend on the geologic setting and data quality. Class 3 DHIs are usually interpreted on full stack volumes and/or offset/angle volumes and their associated derivative products. Class 2 DHIs are typically interpreted on offset/angle volumes (especially far offset/angle volumes), gathers, and their associated derivative products including various types of crossplots. The relationships between attributes and DHI characteristics can be variable depending on the geologic setting and the seismic data quality. If it is unclear which attributes to employ, principal component analysis (PCA) can assist interpreters. PCA is a linear mathematical technique to reduce a large set of variables (seismic attributes) to a smaller set that still contains most of the variation of independent information in the larger set. In other words, PCA helps to determine the most meaningful seismic attributes.
The first principal component accounts for as much of the variability in the data as possible and each succeeding component (orthogonal to each preceding) accounts for as much of the remaining variability. Given a set of seismic attributes generated from the same original volume, PCA can identify combinations of attributes producing the largest variability in the data suggesting these combinations of attributes that will better identify specific geologic features of interest and in this case specific DHI characteristics. Even though the first principal component represents the largest linear attribute combinations that best represents the variability of the bulk of the data, it may not identify specific features of interest to the interpreter. The interpreter should also evaluate succeeding principal components because they may be associated with DHI characteristics not identified with the first principal component. In fact, the top contributing seismic attributes from the first few principal components, when combined, often produce the best results for DHI delineation. In other words, PCA is a tool that, employed in an interpretation workflow with a geoscientist’s knowledge of DHI related attributes, can give direction to meaningful seismic attributes and improve interpretation results. It is logical, therefore, that a PCA evaluation may provide important information on appropriate seismic attributes to take into a self-organizing map generation.

After appropriate seismic attributes have been selected, the next level of interpretation requires pattern recognition and classification of often subtle information embedded in the seismic attributes. Taking advantage of today’s computing technology, visualization techniques, and understanding of appropriate parameters, self-organizing maps (SOMs) efficiently distill multiple seismic attributes into classification and probability volumes (Smith and Taner, 2010; Roden et al., 2015). Developed by Kohonen in 1982 (Kohonen, 2001), SOM is a powerful non-linear cluster analysis and pattern recognition approach that helps interpreters to identify patterns in their data that can relate to geologic features and DHI characteristics. The samples for each of the selected seismic attributes from the desired window in a 3D survey are placed in attribute space where they are normalized or standardized to the same scale. Also in attribute space are neurons, which are points in space that start at random locations and train from the attribute data and mathematically hunt for natural clusters of information in the seismic data. After the SOM analysis, each neuron will have identified a natural cluster as a pattern in the data. These clusters reveal significant information about the classification structure of natural groups that are difficult to view any other way. In addition to the resultant classification volume, a probability volume is also generated which is a measure of the Euclidean distance from a data point to its associated winning neuron (Roden et al., 2015). The winning neuron is the one that is nearest to the data point in attribute space. It has been discovered that a low classification probability corresponds to areas that are quite anomalous as opposed to high probability zones that relate to regional and common events in the data.

To interpret the SOM classification results, each neuron is displayed in a 2D color map. Highlighting a neuron or combination of neurons in a 2D color map identifies their associated natural clusters or patterns in the survey because each seismic attribute data point retains its physical location in the 3D survey. The identification of these patterns in the data enables interpreters to define geology not easily interpreted from conventional seismic amplitude displays alone. These visual cues are facilitated by an interactive workstation environment.

Low probability anomalies

After the SOM process and natural clusters have been identified, Roden et al. (2015) describe the calculation of a classification probability. This probability estimates the probable certainty that a winning neuron classification is successful. The classification probability ranges from zero to 100% and is based on goodness of fit of the Euclidean distances between the multi-attribute data points and their associated winning neuron. Those areas in the survey where the classification probability is low correspond to areas where no winning neurons fit the data very well. In other words, anomalous regions in the survey are noted by low probability. DHI characteristics are often associated with low classification probabilities because they are anomalous features that are usually not widespread throughout the survey.

SOM analysis for Class 3 DHI characteristics

A class 3 geologic setting is associated with low acoustic impedance reservoirs that are relatively unconsolidated. These reservoirs typically have porosities greater than 25% and velocities less than 2700 m/sec. The following DHI characteristics are identified by multi-attribute SOM analyses in an offshore Gulf of Mexico class 3 setting. This location is associated with a shallow oil and gas field (approximately 1200 m) in a water depth of 140 m that displayed a high seismic amplitude response. Two producing wells with approximately 30 m of pay each were drilled in this field on the upthrown side of an east-west trending normal fault. Before these wells were drilled, operators had drilled seven unsuccessful wells in the area based on prominent seismic amplitudes that were either wet or low saturation gas. Therefore, the goal was to identify as many DHI characteristics as possible to reduce risk and accurately define the field and to develop SOM analysis approaches that can help to identify other possible prospective targets in the area.

Initially, 20 instantaneous seismic attributes were run through a PCA analysis in a zone 20ms above and 150 ms below the top of the mapped producing reservoir. Based on these PCA results, various combinations of attributes were employed in different SOM analyses with neuron counts from 3X3, 5X5, 8X8, 10X10, and 12X12 employed for each set of seismic attributes. It is from this machine learning multi-attribute interpretation workflow that the results defining different DHI characteristics were interpreted and described below. All of the figures associated with this example are from a SOM analysis with a 5X5 neuron count and employed the instantaneous attributes listed below.

  • Sweetness
  • Envelope
  • Instantaneous Frequency
  • Thin Bed
  • Relative Acoustic Impedance
  • Hilbert
  • Cosine of Instantaneous Phase
  • Final Raw Migration

SOM classification of a reservoir

Figure 1 From the top of the producing reservoir: a) time structure map in contours with an amplitude overlay in colour and b) SOM classification with low probability less than 1% denoted by white areas. The yellow line in b) represents with downdip edge of the high amplitude zone designated in a).

Figure 1a displays a time structure map as denoted by the contours with an amplitude overlay (color) from the mapped top of the reservoir in this field. The horizon at the top of the reservoir was picked on a trough (low impedance) on zero phase seismic data (SEG normal polarity). Figure 1a indicates that there is a relatively good amplitude conformance to structure based on the amplitude. Figure 1b is a display of classification probability from the SOM analysis at the top of the reservoir at the same scale as Figure 1a. This indicates that the top of this reservoir exhibits an anomalous response from the SOM analysis where any data points with a probability of less than 1% are displayed in the white areas. In comparing Figure 1a and 1b it is apparent that the low probability area corresponds closely to the amplitude conformance to structure as denoted by the yellow outline in Figure 1b. This confirms the identification of the productive area with low probability and proves the efficacy of this SOM approach. The consistency of the low probability SOM response in the field is another positive DHI indicator. In fact, the probabilities as low as .01% still produce a consistent response over the field indicating how the evaluation of low probability anomalies is critical in the interpretation of DHI characteristics.

This field contains oil with a gas cap and before drilling, there were hints of possible flat spots suggesting hydrocarbon contacts on the seismic data, but the evidence was inconsistent and not definitive. Figure 2 displays a north-south vertical inline profile through the middle of the field and its location is denoted in Figure 1. Figure 2a exhibits the initial stacked amplitude data with the location of the field annotated. Figure 2b denotes the SOM analysis results of this same vertical inline 9411 which incorporated the eight instantaneous attributes listed above in a 5X5 neuron matrix. The associated 2D color map in Figure 2b denotes the 25 natural patterns or clusters identified from the SOM process. It is apparent in this figure that the reservoir and portions of the gas/oil contact and the oil/water contact are easily identified. This is more easily seen in Figure 2c where the 2D color map indicates that the neurons highlighted in grey (20 and 25) are defining the hydrocarbon-bearing portions of the reservoir above the hydrocarbon contacts and the flat spots interpreted as hydrocarbon contacts are designated by the rust-colored neuron (15). The location of the reservoir and hydrocarbon contacts are corroborated by well control. The southern edge of the reservoir is revealed in the enlargements of the column displays on the right. Downdip of the field is another undrilled anomaly defined by the SOM analysis that exhibits similar DHI characteristics identified by the same neurons.

stacked seismic amplitude display 2

Figure 2 North-south vertical profile 9411 through the middle of the field: a) stacked seismic amplitude display with the field location designated, b) SOM classification with 25 neurons indicated by the 2D colour map over a 170 ms window, and c) three neurons highlighting the reservoir above the oil/water and gas/oil contacts and the hydrocarbon contacts (flat spots). The expanded insets denote the details from the SOM results at the downdip edge of the field.

stacked seismic amplitude display 2

Figure 3 West-east vertical profile 3183 through the field: a) stacked seismic amplitude display denoting tie with line 9411, b) SOM classification with 25 neurons indicated by the 2D colour map, and c) three neurons highlighting the gas/oil and oil/water contacts and the hydrocarbon contacts (flat spots). The expanded insets clearly display the edge of the field in the SOM classifications.

West to east crossline 3179 over the field is displayed in Figure 3 and with it the location designated in Figure 1. The stacked seismic amplitude display of Figure 3a indicates that its tie with inline 9411 is located in the updip portion of the reservoir where there is an apparent gas/oil contact. Figure 3b exhibits the SOM results of this west-east line utilizing 25 neurons as designated by the 2D color map. Similar to Figure 2b, Figure 3b indicates that the SOM analysis has clearly defined the reservoir by the grey neurons (20 and 25) and the hydrocarbon contacts in the rust-colored neuron (15). Towards the west, the rust-colored neuron (15) denotes the oil/water contact as defined by the flat spot on this crossline. Figure 3c displays only neurons 15, 20, and 25 to clearly define the reservoir, its relationship above the hydrocarbon contacts, and the contacts themselves. The three enlargements on the left are added for detail.

What is very evident from the SOM results in both Figures 2 and 3 is a clear character change and definition of the downdip edges of the reservoir. The downdip edge definition of an interpreted trap is an important DHI characteristic that is clearly defined by the SOM analysis in this field. The expanded insets in Figures 2 and 3 indicate that the SOM results are producing higher resolution results than the amplitude data alone and the edge terminations of the field are easily interpreted. These results substantiate that the SOM process with the appropriate set of seismic attributes can exhibit thin beds better than conventional amplitude data.

SOM analysis for Class 2 DHI characteristics

A class 2 geologic setting contains reservoirs more consolidated than class 3 and the acoustic impedance of the reservoirs are about equal to the encasing sediments. Typical porosities range from 15 to 25% and velocities 2700-3600 m/sec for these reservoirs. In class 2 settings, AVO attributes play a larger role in the evaluation of DHI characteristics than in class 3 (Roden et al., 2014). This example is located onshore Texas and targets Eocene sands at approximately 1830 m deep. The initial well B was drilled just downthrown on a small southwest-northeast regional fault, with a subsequent well drilled on the upthrown side (Well A). The reservoirs in the wells are approximately 5-m thick and composed of thinly laminated sands. The tops of these sands produce a class 2 AVO response with near zero amplitude on the near offsets and an increase in negative amplitude with offset (SEG normal polarity).

time structure map

Figure 4 Time structure map at the top of the producing Eocene reservoir.

The goal of the multi-attribute analysis was to determine the full extent of the reservoirs revealed by any DHIs because both wells were performing much better than the size of the amplitude anomaly indicated from the stack and far offset seismic data. Figure 4 is a time-structure map from the top of the Eocene reservoir. This map indicates that both wells are located in stratigraphic traps with Well A situated on southeast dip and Well B located on the northwest dip that terminates into the regional fault. The defined anomaly conformance to downdip closure cannot be seen in the Well A reservoir because the areal extent of the reservoir is in a north-south channel and the downdip conformance location is
very narrow. In the Well B reservoir, the downdip edge of the reservoir actually terminates into the fault so an interpretation of the downip conformance cannot be determined. The updip portion of the reservoir at Well B actually thins out towards the south-east forming an updip seal for the stratigraphic trap. The Well B reservoir was interpreted to have a stacked data amplitude anomaly of approximately 70 acres and the Well A reservoir was determined to only have an amplitude anomaly of only about 34 acres (Figure 5a).

Amplitude -SOM classification

Figure 5 At the top of the Eocene reservoir: a) stacked seismic amplitude, b) SOM classification with 64 neurons, and c) same classification as the middle display with low probability of less than 30% designated by the white areas.

Conventional-Stacked-Seismic-Amplitude-Display-optimized

Figure 6 North-south arbitrary line through Wells A and B with the location designated in Figure 4: a) stacked seismic amplitude display, b) SOM classification with 64 neurons indicated by the 2D colour map, and c) SOM classification with only four neurons in grey highlighting both the reservoirs associated with the wells.

The gathers associated with the 3D PSTM survey over this area were conditioned and employed in the generation of very specific AVO attributes conducive to the identification of class 2 AVO anomalies in this geologic setting. The ten AVO attributes used for the SOM analysis were selected from a PCA analysis of 18 AVO attributes. The AVO attributes that were selected for the SOM analysis are listed below:

  • Far – Near
  • Shuey 2 term approximation – Intercept
  • Shuey 2 term approximation – Gradient
  • Shuey 2 term approximation – 1/2 (Intercept + Gradient)
  • Shuey 2 term approximation – 1/2 (Intercept – Gradient)
  • Shuey 3 term approximation – Intercept
  • Shuey 3 term approximation – Gradient
  • Shuey 3 term approximation – 1/2 (Intercept + Gradient)
  • Verm-Hilterman approximation – Normal Incident
  • Verm-Hilterman approximation – Poisson’s Reflectivity

Several different neuron counts were generated with these ten AVO attributes and the results in the associated figures are from the 8X8 (64 neurons) count. Figure 5b displays the SOM results from the top of the Eocene reservoirs. The associated 2D color map indicates that neurons 47, 58, 62, and 63 are defining the reservoirs drilled by the two wells. Comparing the areal distribution of the amplitude defined reservoirs in 5a to the SOM defined reservoirs in Figure 5b indicates that the later is larger. In fact, the Well A amplitude defined area of 34 acres is compared to approximately 95 acres as denoted by four neurons in Figure 5b. The Well B amplitude defined reservoir area was determined to be 70 acres, whereas, the SOM defined area was determined to be approximately 200 acres. The SOM defined areal distributions were determined to be consistent with engineering and pressure data in the two wells. The anomaly consistency in the mapped target area is evident in Figure 5b and is better in defining the extent of the producing reservoirs than amplitudes.

Figure 5c displays the SOM results of 5b. However, less than 30% of the low classification probability results are displayed in white. It denotes that the core of the reservoirs at each of the well locations reveal low probability. Low probability is defining anomalous zones based on the ten AVO attributes run in the SOM classification process.

 

Stacked Seismic Amplitude Display 3

Figure 7 Northeast-southwest inline 2109 through Well B with location designated in Figure 4: a) stacked seismic amplitude display, b) SOM classification with 64 neurons as denoted by the 2D colour map, and c) SOM classification with only four grey neurons highlighting the reservoir at Well B. The expanded insets display the updip edges of the reservoir with the SOM results clearly defining the updip seal edge of the field.

 

Figure 6 is a north-south arbitrary line running through both Wells A and B with its location denoted in Figure 4. Figure 6a is the conventional stacked seismic amplitude display of this line. Figure 6b displays the SOM results and the reservoirs at both wells defined by neurons 47, 58, 62, and 63. In Figure 6c only these four neurons are turned on defining the location of the reservoirs on this line. The four neurons are clearly defining the field and the southern downdip limits of the reservoir associated with Well A and the updip limits of the reservoir at Well B where the sands are thinning out to the south. Figure 7 is northwest-southeast inline 2109 with its location denoted in Figure 4. Figure 7a is the stacked amplitude display and Figure 7b displays the SOM results defining the limits of the Well B reservoir as it terminates at the fault to the northwest. Figure 7c with only the four neurons defining the reservoir displayed indicates the thinning out of the reservoir updip much more clearly than with amplitudes alone. The insets of Figures 7b and 7c illustrate the details in the updip portion of the reservoir defined by the SOM process. The SOM analysis incorporates ten AVO attributes and is not limited by conventional amplitude/frequency limitations of thickness and areal distribution. The AVO attributes selected for this SOM analysis are specifically designed to bring out the appropriate AVO observations for a class 2 setting. It is clear from these results that the AVO attributes in this SOM analysis are clearly distinguishing the anomalous areas associated with the producing reservoirs from the equivalent events and zones outside these stratigraphic traps.

Conclusions

For more than 40 years seismic amplitudes have been employed to interpret DHIs in an attempt to better define prospects and fields. There are dozens of DHI characteristics associated primarily with class 2 and 3 geologic settings. Hundreds of seismic attributes have been developed in an effort to derive more information from the original seismic amplitude data and further improve DHI interpretations. A machine learning workflow incorporating seismic attributes, PCA, and SOM, has been proven to produce excellent results in the interpretation of DHIs. This machine learning workflow was applied to data in class 2 and 3 reservoirs in an effort to interpret the most important DHI characteristics as defined by a worldwide industry database. The SOM analysis employing instantaneous attributes in a class 3 setting successfully identified the top DHI characteristics and especially those defining edge effects and hydrocarbon contacts (flat spots). AVO attributes conducive to providing information in class 2 settings incorporated in a SOM analysis allowed the interpretation of DHI characteristics that better defined the areal extent of the producing reservoirs than amplitudes by clearly denoting the stratigraphic trap edges.

Low SOM classification probabilities have been proven to help identify DHI characteristics. These low probabilities relate to data regions where the attributes are very different from the data points of all of the attributes in the SOM analysis and their associated winning neurons, which has defined a natural cluster or pattern in the data. Anomalous regions in the data, for example, DHI characteristics, are noted by low probability. This analytical approach of defining low probabilities proved to be helpful in identifying DHI characteristics in both class 2 and 3 settings.

An important observation in these two case studies is that the use of appropriate seismic attributes in a SOM analysis can not only identify DHI characteristics not initially interpreted but can also increase or decrease confidence in already identified characteristics. This multi-attribute machine learning workflow provides a methodology to produce more accurate identification of DHI characteristics and a better risk assessment of a geoscientist’s interpretation.

Acknowledgments

The authors would like to thank the staff of Geophysical Insights for the research and development of the machine learning applications used in this paper. We would also like to thank the Rose & Associates DHI consortium, which has provided extremely valuable information on DHI characteristics. The seismic data in the offshore case study is courtesy of Petroleum Geo-Services. Thanks also go to Deborah Sacrey and Mike Dunn for reviewing the paper. Finally, we would like to thank Tom Smith for reviewing this paper and for the inspiration to push the boundaries of interpretation technology.

References

Brown, A.B, [2004]. Interpretation of three-dimensional seismic data. AAPG Memoir 42/SEG Investigations in Geophysics No. 9, sixth edition.

Chen, Q. and Sidney, S. [1997]. Seismic attribute technology for reservoir forecasting and monitoring. The Leading Edge, 16, 445-448. Chopra, S. and Marfurt, K. [2007]. Seismic attributes for prospect identification and reservoir characterization. SEG Geophysical Development Series No. 11.

Fahmy, W.A. [2006]. DHI/AVO best practices methodology and applications: a historical perspective. SEG/EAGE Distinguished Lecture presentation.

Forrest, M., Roden, R. and Holeywell, R. [2010]. Risking seismic amplitude anomaly prospects based on database trends. The Leading Edge, 5, 936-940.

Hilterman, F.J. [2001]. Seismic amplitude interpretation. Distinguished instructor short course, SEG/EAGE. Kohonen, T. [2001]. Self Organizing Maps. Third extended addition, Springer Series in Information Services, Vol. 30.

Roden, R., Forrest, M. and Holeywell, R. [2005]. The impact of seismic amplitudes on prospect risk analysis. The Leading Edge, 7, 706-711.

Roden, R., Forrest, M. and Holeywell, R. [2012]. Relating seismic interpretation to reserve/resource calculations: Insights from a DHI consortium. The Leading Edge, 9, 1066-1074.

Roden, R., Forrest, M., Holeywell, R., Carr, M. and Alexander, P.A. [2014]. The role of AVO in prospect risk assessment. Interpretation, 2, SC61-SC76.

Roden, R., Smith, T. and Sacrey, D. [2015]. Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing maps. Interpretation, 3, SAE59-SAE83.

Rudolph, K.W. and Goulding, F.J. [2017]. Benchmarking exploration predictions and performance using 20+ yr of drilling results: One company’s experience. AAPG Bulletin, 101, 161-176.

Rutherford, S.R. and Williams, R.H. [1989]. Amplitude-versus-offset variations in gas sands: Geophysics, 54, 680-688.

Smith, T. and Taner, M.T. [2010]. Natural clusters in multi-attribute seismics found with self-organizing maps. Extended Abstracts, Robinson-Treitel Spring Symposium by GSH/SEG, March 10-11, 2010, Houston, Tx.

Taner, M.T. [2003]. Attributes revisited. http://www.rocksolidimages.com/pdf/attrib_revisited.htm, accessed 13 August 2013.

Rocky RodenROCKY RODEN owns his own consulting company, Rocky Ridge Resources Inc., and works with several oil companies on technical and prospect evaluation issues. He also is a principal in the Rose and Associates DHI Risk Analysis Consortium and was Chief Consulting Geophysicist with Seismic Micro-technology. He is a proven oil finder (36 years in the industry) with extensive knowledge of modern geoscience technical approaches (past Chairman – The Leading Edge Editorial Board). As Chief Geophysicist and Director of Applied Technology for Repsol-YPF, his role comprised advising corporate officers, geoscientists, and managers on interpretation, strategy and technical analysis for exploration and development in offices in the U.S., Argentina, Spain, Egypt, Bolivia, Ecuador, Peru, Brazil, Venezuela, Malaysia, and Indonesia. He has been involved in the technical and economic evaluation of Gulf of Mexico lease sales, farmouts worldwide, and bid rounds in South America, Europe, and the Far East. Previous work experience includes exploration and development at Maxus Energy, Pogo Producing, Decca Survey, and Texaco. He holds a BS in Oceanographic Technology-Geology from Lamar University and a MS in Geological and Geophysical Oceanography from Texas A&M University. Rocky is a member of SEG, AAPG, HGS, GSH, EAGE, and SIPES.
ChingWen Chen, seismic interpreterCHINGWEN CHEN, PH.Dreceived an M.S. (2007) and a Ph.D. (2011) in Geophysics from the University of Houston, studying global seismology. After graduation, she joined the industry as a geophysicist with Noble Energy where she supported both exploration and development projects. Dr. Chen has a great passion for quantitative seismic interpretation, and more specifically rock physics, seismic imaging and multi-seismic attribute analysis. She later joined Geophysical Insights as a Senior Geophysicist, where the application of machine learning techniques became a focus of her work. Since 2015, her primary interest has been in increasing the efficiency of seismic interpretation.