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

2D Colormap

A graphical representation of neuron classifications of attributes.  Each hexagonal object (neuron) in the interactive 2D colormap represents a pattern or cluster in the data and potentially a geologic feature of interest. The 2D colomap is used interactively with the Paradise Universal Viewer to select and isolate specific neurons which have a classified set of seismic attributes according to where the data is concentrated.

Batching vs. Interactive Technologies 

While a SOM or PCA run are example of batching applications, other features within Paradise are interactive, such as the 2D Colormap and Universal Viewer, which respond immediately to commands via the graphical user interface.  Therefore, Paradise has both batching and interactive capabilities.  

Geobody Analysis 

A tool in Paradise that quantifies the relative contribution of attributes within a neuron or set of neurons.  The 2D Colormap reveals the specific attributes comprising a selected classification result as represented by each neuron on the 2D Colormap.  Then, the interpreter can run a SOM across the refined area to expose geobodies having similar properties.   Note:  This feature will be available in Paradise 3.0.

Machine Learning

A process by which computer algorithms learn iteratively from the data and adapt independently to produce reliable, repeatable results.  Machine learning addresses two significant issues: 

  • The big data problem of trying to interpret dozens, if not hundreds, of volumes of data
  • The fact that humans cannot understand the relationship of several types of data all at once


Multi-Attribute Analysis

A beneficial technique when single attributes are indistinct.  These natural patterns or clusters represent geologic information embedded in the data, and can help identify geologic features, geobodies, and aspects of geology that often cannot be interpreted by any other means. 

Neural Network

A class of machine learning.  While there are several forms of applying neural networks, Paradise uses the Self-Organizing Map (SOM) process, which is sometimes referred to as Kohenen maps after Professor Teuvo Kohenen at the University of Finland.  


As expressed in Paradise, a neuron is a mathematical construct representing a class of data from multiple attributes analyzed simultaneously using a Self-Organizing Map (See SOM).  The 2D Colormap in Paradise is composed of the number of neurons prescribed by the user in setting up the neural processing and SOM run.  Consequently, neurons can be any designated number but 25 (5X5), 64 (8X8) or 100 (10X10) neurons are the most commonly used configurations of neural processing represented in the 2D Colormap.

Principal Component Analysis (PCA) 

Attributes differ in their relative contribution to information in a given volume.  PCA is a linear process that helps to determine those attributes that have the greatest contribution to the data and quantifying the relative contribution of each attribute based on its variance. The results of the PCA are given in 2 bar charts – Eigenvalues and Eigenvectors.  Together, they indicate the direction and magnitude of the greatest variance among the set of attributes.

Eigenvalue –  Shows how much variance there is in the set of attributes in the PCA and can be selected at any time to reveal its corresponding set of Eigenvectors.
Eigenvector –  The graphical bar chart and associated table listing the relative contribution on a percentage basis of each attribute in a set.  



Seismic Attribute 

Any measurable property of seismic data which aids interpreters in identifying geologic features that are not understood clearly in the original data

Self-Organizing Map (SOM) 

A neural network based, machine learning process that is applied to multiple attribute volumes simultaneously. A SOM analysis enables interpreters to identify the natural organizational patterns in the data from multiple seismic attributes.  Applied at full seismic resolution in Paradise, the SOM produces a non-linear classification of the data in a region designated by the interpreter.  Regions can be delimited by time, between horizons, or above and below a given horizon.  SOM evaluations have proven to be beneficial in essentially all geologic settings, including unconventional resource plays, moderately compacted onshore regions, and offshore unconsolidated sediments. 


Universal Viewer

Presents SOM process results through classification and probability volumes.  Displays 2D and 3D views of the data while using the 2D colormap to gain understanding of the classification results.