Geophysical Insights hosting the 2018 OIl & Gas Machine Learning Symposium in Houston on September 27, 2018
Dr. Tom Smith presenting on Machine Learning at the 3D Seismic Symposium on March 6th in Denver
What is the "holy grail" of Machine Learning in seismic interpretation? by Dr. Tom Smith, GSH Luncheon 2018
Using Attributes to Interpret the Environment of Deposition - A Video Course. Taught by Kurt Marfurt, Rocky Roden, and ChingWen Chen
Dr. Kurt Marfurt and Dr. Tom Smith featured in the July edition of AOGR on Machine Learning and Multi-Attribute Analysis

Using Self-Organizing Maps to Explore the Yegua in the Texas Gulf Coast

Paradise Application Brief

Exploring shallow Yegua formation as an independent method to accurately identify anomloies and exposing direct hydrocarbon indicators using Self-Organizing Map (SOM) analysis to enhance conventional seismic interpretation to reveal anomolies.

Click here to download the PDF

Full Article Text:

Analysis of Middle Texas Gulf Coast 3D to explore for shallow Yegua Formation Potential: 

In this case study of the use of Self-Organizing-Maps (SOM analysis), the gathers were used to generate AVO volumes such as Far-Near (used on the angle stacks, where nears were 0-15 degrees and fars were 31-45 degrees), (Far-Near)xFar, Gradient (B), Intercept (A) x Gradient (B), 1⁄2 (Intercept + Gradient) and Poissons’ Re ectivity (PR).

Conventional amplitude interpretation identified a potential area of hydrocarbon accumulation, downthrown on a down-to-coast fault. Figure 1 is the amplitude extraction from the PSTM-raw volume. 

In addition to the created AVO attributes, volumes of Spectral Decomposition, curvature, similarity and other frequency-related attributes were created. Conventional interpretation of the reservoir area indicated the anomaly covered approximately 70 acres. 

A SOM of the above mentioned AVO attributes, plus Sweetness and Average Energy was run to more closely identify the anomaly and the aerial extent. Figure 2 shows the results of this analysis. 

A detailed engineering study of the production indicates that the results of the SOM analysis concurs with the aerial extent of the sand
deposition to be more in line with almost SOM Classification Yegua 3 Base 400 acres of drainage rather than the initial 70 acres rst identi ed. The SOM identified in this time slice shows a network of sand deposition not seen in conventional mapping. 

Figure 3 shows an arbitrary line going through a second, upthrown Yegua anomaly identi ed by the SOM analysis, and now drilled, confirming the economic presence of hydrocarbons. 

The conclusion drawn from this study is that SOM analysis proved to complement and enhance the conventional interpretation by providing a second, completely independent method of exposing direct hydrocarbon indicators.