Artificial immune-based self-organizing maps for seismic-facies analysis

Abstract

Seismic facies, combined with well-log data and other seismic attributes such as coherency, curvature, and AVO, play an important role in subsurface geological studies, especially for identification of depositional structures. The effectiveness of any seismic facies analysis algorithm depends on whether or not it is driven by local geologic factors, the absence of which may lead to unrealistic information about subsurface geology, depositional environment, and lithology. This includes proper identification of number of classes or facies existing in the data set. We developed a hybrid waveform classification algorithm based on an artificial immune system and self-organizing maps (AI-SOM), that forms the class of unsupervised classification or automatic facies identification followed by facies map generation. The advantage of AI-SOM is that, unlike, a stand-alone SOM, it is more robust in the presence of noise in seismic data. Artificial immune system (AIS) is an excellent data reduction technique providing a compact representation of the training data; this is followed by clustering and identification of number of clusters in the data set. The reduced data set from AIS processing serves as an excellent input to SOM processing. Thus, facies maps generated from AI-SOM are less affected by noise and redundancy in the data set. We tested the effectiveness of our algorithm with application to an offshore 3D seismic volume from F3 block in the Netherlands. The results confirmed that we can better interpret an appropriate number of facies in the seismic data using the AI-SOM approach than with a conventional SOM. We also examined the powerful data-reduction capabilities of AIS and advantages the of AI-SOM over SOM when data under consideration were noisy and redundant.

Seismic facies analysis through musical attributes

“…; Chopra and Marfurt ). In fact, one of the most attractive applications of SOMs in typical problems regarding seismic facies analysis has been performed by Saraswat and Sen (). In that case, an algorithm emulating the typical interaction mechanism of vertebrates’ immune system is used to reduce the dimensionality of seismic data before SOM clustering.…”

Facies analysis by integrating 3D seismic attributes and well logs for prospect identification and evaluation — A case study from Northwest China

“…In the past few decades, huge efforts have been made in deriving new seismic attributes and in the application of seismic attributes to subsurface exploration (Taner et al, 1979;Marfurt et al, 1999;Marfurt and Kirlin, 2001; Al-Dossary and Marfurt, 2006;Marfurt, 2006). Seismic facies analysis that combines seismic attributes and well logs has been successfully applied to identify depositional facies and for hydrocarbon exploration (Zeng, 2004;Michelena et al, 2011;Saraswat and Sen, 2012). Comparing the patterns (configuration, amplitude, continuity, and frequency) of a group of reflected waveform is the main consideration and means for seismic facies analysis (Zeng, 2004).…”

“…Comparing the patterns (configuration, amplitude, continuity, and frequency) of a group of reflected waveform is the main consideration and means for seismic facies analysis (Zeng, 2004). The efforts, which have been put on seismic facies analysis, can be classified into two categories: (1) developing new seismic attributes to better highlight different facies (e.g., Gao, 2011) and (2) developing new multivariable classification algorithms or applying existing pattern recognition and clustering algorithms to multiple seismic attributes (Balch, 1971;Taner et al, 1979;Saggaf et al, 2003;Marroquín et al, 2009;Saraswat and Sen, 2012;Zhao et al, 2015). The use of pattern recognition and classification began soon after the development of seismic attributes (Balch, 1971;Taner et al, 1979).…”

Multiattribute Seismic Analysis With Fractal Dimension and 2D and 3D Continuous Wavelet Transform

“…There has been a significant number of seismic attributes since 1970s. With the introduction of complex trace analysis and acoustic impedance (Lavergne and Willm 1977;Taner et al 1979), numerous attributes on the basis of mathematics (Chakraborty and Okaya 1995;Taner et al 1979;Sinha et al 2005), neural networks (Coléou et al 2003;Matos et al 2007;Saraswat and Sen 2012), texture analysis (Chopra and Alexeev 2006;Yenugu and Marfurt 2010), and volume and horizon were introduced. It is currently a common practice to render two or more attributes simultaneously to perform some kind of multiattribute analysis.…”