Geophysical Insights hosting the 2018 Oil & Gas Machine Learning Symposium in Houston on September 27, 2018
Introduction to Machine Learning for Multi–Attribute Interpretation and AASPI attributes - A 1-day, DGS Continuing Education course in Denver, CO on September 18th
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

Comprehensive interpretation services - leveraging advanced technology

Working closely with the client team, Geophysical Insights provides complete interpretation services that accelerate prospect evaluation and reduce exploration risk through greater insight into seismic and engineering data. Leveraging the Paradise® geoscience analysis platform and other tools, our consulting services address both conventional and unconventional geologic environments. 

In a conventional setting, the application of Paradise typically means analyzing multiple sets of seismic attributes to expose Direct Hydrocarbon Indicators (DHI's), reveal geologic and stratigraphic features, and highlight zones of high pore pressure. In an unconventional shale plays, our work focuses on defining regional/local fracture and fault trends which help identify optimal drilling locations, directions and completions techniques, and generating analysis that is used to identify sweet spots.

Applying extensive industry experience and advanced interpretation technology, we offer clients...

  • A thorough assessment that identifies the best set of seismic attributes to be analyzed
  • Multiple (typically 3) PCA and SOM based analysis results from corresponding sets of seismic attributes
  • An appropriate interpretation for the geologic trends in which the client is interested
  • A selection of well information for calibration purposes to bring ground truth to the seismic response
  • Two new attribute volumes - a neural network classification and a classification probability
  • A distillation of the prospect to geobodies that deserve a more detailed investigation

Applying neural network technology to attributes reveals a deeper understanding of the seismic data

SOM Classification

Conventional Seismic Display

Conventional Seismic Display
Neural Network Classification

Applying Paradise to multiple attributes simultaneously dramatically increases the resolution and insight into seismic data.

Conventional seismic data has limited
resolution compared to well log information.

Our consultants apply Paradise to create deeper insights in the seismic response, which de-risks an area of interest or exposes new opportunities

SOM Attribute Perspective

SOM Survey Space Perspective

Survey Perspective

A 3D survey with a single attribute provides a limited understanding of seismic properties. Today, we work with many attributes. Three attributes are illustrated, in the figure above, from a single 3D survey. The three points near the center depict one data sample for three associated attributes.

Attribute Space

In this simple illustration, each data point sample is plotted in attribute space along three attribute axes, resulting in a natural cluster of similar characteristics. Two additional natural clusters are illustrated above. Initially, neurons are randomly placed in attribute space. In the "learning" stage, neurons are attracted to the data samples in the clusters. Ultimately, the neurons reveal subtle combinations of attributes that may highlight the presence and types of hydrocarbons.

Contact us to explore how the advanced pattern recognition workflows in Paradise can reduce exploration risk.