Atish Roy

A comparison of classification techniques for seismic facies recognition

AbstractDuring the past decade, the size of 3D seismic data volumes and the number of seismic attributes have increased to the extent that it is difficult, if not impossible, for interpreters to examine every seismic line and time slice. To address this problem, several seismic facies classification algorithms including k-means, self-organizing maps, generative topographic mapping, support vector machines, Gaussian mixture models, and artificial neural networks have been successfully used to extract features of geologic interest from multiple volumes. Although well documented in the literature, the terminology and complexity of these algorithms may bewilder the average seismic interpreter, and few papers have applied these competing methods to the same data volume. We have reviewed six commonly used algorithms and applied them to a single 3D seismic data volume acquired over the Canterbury Basin, offshore New Zealand, where one of the main objectives was to differentiate the architectural elements of a tu...

Characterizing a Mississippian tripolitic chert reservoir using 3D unsupervised and supervised multiattribute seismic facies analysis: An example from Osage County, Oklahoma

AbstractSeismic interpretation is based on the identification of reflector configuration and continuity, with coherent reflectors having a distinct amplitude, frequency, and phase. Skilled interpreters may classify reflector configurations as parallel, converging, truncated, or hummocky, and use their expertise to identify stratigraphic packages and unconformities. In principal, a given pattern can be explicitly defined as a combination of waveform and reflector configuration properties, although such “clustering” is often done subconsciously. Computer-assisted classification of seismic attribute volumes builds on the same concepts. Seismic attributes not only quantify characteristics of the seismic reflection events, but also measure aspects of reflector configurations. The Mississippi Lime resource play of northern Oklahoma and southern Kansas provides a particularly challenging problem. Instead of defining the facies stratigraphically, we need to define them either diagenetically (tight limestone, stra...

Generative topographic mapping for seismic facies estimation of a carbonate wash, Veracruz Basin, southern Mexico

AbstractSeismic facies estimation is a critical component in understanding the stratigraphy and lithology of hydrocarbon reservoirs. With the adoption of 3D technology and increasing survey size, manual techniques of facies classification have become increasingly time consuming. Besides, the numbers of seismic attributes have increased dramatically, providing increasingly accurate measurements of reflector morphology. However, these seismic attributes add multiple “dimensions” to the data greatly expanding the amount of data to be analyzed. Principal component analysis and self-organizing maps (SOMs) are popular techniques to reduce such dimensionality by projecting the data onto a lower order space in which clusters can be more readily identified and interpreted. After dimensional reduction, popular classification algorithms such as neural net, K-means, and Kohonen SOMs are routinely done for general well log prediction or analysis and seismic facies modeling. Although these clustering methods have been ...

Applying Self-organizing Maps of Multiple Attributes, an Example From the Red-Fork Formation, Anadarko Basin

Summary The self-organizing map (SOM) is one of the most effective pattern recognition techniques, and is commonly used tool for non-supervised seismic facies analysis. Early SOM implementations required estimating the number of clusters. Current implementations avoid this choice by over-defining the number of clusters and mapping them against continuous 1D, 2D and 3D colorbars, which the interpreter then visually clusters. We generate SOM clusters based on the wavelet shape, on the spectral component and the GLCM attributes of the Red-Fork formation and correlate the results with the knowledge of geology from extensive well control in the area.

Cluster Assisted 3D And 2D Unsupervised Seismic Facies Analysis, an Example From the Barnett Shale Formation In the Fort Worth Basin, Texas.

Summary The most popular seismic attributes fall into broad categories – those that are sensitive to lateral changes in waveform and structure, such as coherence and curvature, and those that are sensitive to lithology and fluid properties – such as AVO and impedance inversion. Unfortunately neither of these two attribute families works well in differentiating the depositional packages characterized by subtle changes in the stratigraphic column or lateral changes in texture. Automatic seismic facies analysis aims to classify similar seismic traces based on amplitude, phase, frequency and other seismic attributes. This paper reviews Kohonen Self Organizing Maps as one of the clustering algorithms that can generate 3D seismic facies volumes and maps using multiple attributes as input. The present area of study is the Mississippian Barnett Shale of the Fort Worth Basin in Texas. The aim of the study is to visualize the variation in shale and possible relationship between these rock types and their seismic expression and try to delineate by passed play after hydraulic fracturing.

Introduction to special section: Pattern recognition and machine learning

The E&P community, both in the industry and academia, is painfully aware of the challenges and complexity of performing seismic interpretation and reservoir characterization in increasingly larger, more intricate, and more heterogeneous data sets. This increase in size is coupled with an emphasis on