Attribute Analysis in Unconventional Resource Plays Using Unsupervised Neural Networks

Analysis of Unconventional Resource using Inversion attributes and seismic attributes

Key elements in understanding unconventional resource plays encompass the following categories:

  • Reservoir Geology: thickness, lateral extent, stratigraphy, mineralogy, porosity and permeability
  • Geochemistry: Total Organic Content (TOC), maturity (Ro-heat), and kerogen% (richness)
  • Geomechanics: acoustic impedance inversion, Young’s modulus, Poisson’s ratio (Vp/Vs) and pressures
  • Faults, Fractures, and Stress Regimes: coherency (similarity), curvature, fault volumes, velocity anisotropy (azimuthal distribution) and stress maps.

This case study involved a newly acquired 3D seismic volume in a fringe area of the Eagle Ford Shale Trend. The 3D is approximately 10 square miles and four wells had been drilled to date on 2D data previously interpreted. Two wells targeted the Eagle Ford Shale Formation, and another two wells were drilled for the Austin Chalk and the Buda Lime Formations. All four wells were drilled in normal-pressured reservoirs with mixed results when it came to quality shows and commercial production. After processing the 3D volume and the initial interpretation was completed, well results and logs were incorporated by the client to create critical inversion attributes known to assist in the assessment of the shale’s productivity. Attributes contributed by the client to the analysis were: Final Density, Lambda Rho, MuRho, Poisson’s Brittleness, Poisson’s Ratio, Shear Impedance, Brittleness Coefficient, and P-impedance. Additional attributes run for the analysis were: Spectral Decomposition volumes, curvature and similarity volumes, Instantaneous attributes and Amplitude-related volumes (Average Energy and sweetness). The zone of study was confined to roughly the Top Austin Chalk to the Top of the Edwards Lime, encompassing the Austin Chalk, Eagle Ford Shale and Buda Limestone, which was approximately from 1.2 to 1.6 seconds. In addition to the PSTM volume, the generated plus client-provided attributes used to highlight sweet spots included:

  • Attenuation
  • Bandwidth
  • Envelope Slope
  • Instantaneous Q
  • MuRho
  • S-Impedance
  • Trace Envelope
  • Young’s Brittleness

A 12 x 6 topology was used for the analysis, so there were 72 neurons training on the attribute information. Figure 1 is a time slice showing the interpreted “sweet spots” in the Eagle Ford Shale on the 3D from the SOM Analysis.

multi attribute analysis for unconventionals

Two wells had been drilled, targeting the Eagle Ford Shale Formation. One was drilled prior to the acquisition of the data, and had few shows. It was plugged as a non-commercial well. The second well had good shows in the horizontal section of the hole, but encountered mechanical difficulties during drilling and had to be temporarily plugged. Figure 2 is an arbitrary seismic line through the deviated borehole of the second well showing the anomalous zone in both the Eagle Ford and Buda Formations and the points at which the well encountered the shows.

seismic attribute analysis for unconventionals

In conclusion, SOM analysis proved to be complementary to the interpretation of the data. The company who owns this 3D is now planning on targeting the area with five additional wells in the coming year. The application of using SOM analysis using selected seismic attributes can dramatically reduce uncertainty and thus decrease exploration risk in unconventional reservoirs.

 

You must log in to access the PDF file. Please log in or register as a user.

 

Welcome Back!

Download PDF here

OR

Request access by filling the form below to download full PDF.

Most Popular Papers
systematic workflow for reservoir thumbnail
Systematic Workflow for Reservoir Characterization in Northwestern Colombia using Multi-attribute Classification
A workflow is presented which includes data conditioning, finding the best combination of attributes for ML classification aided by Principal ...
Read More
identify reservoir rock
Net Reservoir Discrimination through Multi-Attribute Analysis at Single Sample Scale
Published in the special Machine Learning edition of First Break, this paper lays out results from multi-attribute analysis using Paradise, ...
Read More
CNN_facies
Seismic Facies Classification Using Deep Convolutional Neural Networks
Using a new supervised learning technique, convolutional neural networks (CNN), interpreters are approaching seismic facies classification in a revolutionary way ...
Read More
  • Registration confirmation will be emailed to you.

  • We're committed to your privacy. Geophysical Insights uses the information you provide to us to contact you about our relevant content, events, and products. You may unsubscribe from these communications at any time. For more information, check out our Privacy Policy

    Scroll to Top