Significant Advancement in Seismic Reservoir Characterization with Machine Learning
Rocky Roden and Patricia Santogrossi
The application of machine to classify seismic attributes at single sample resolution enhancing reservior characterization.
Compare Seismic Amplitude to SOM Classification
Check out these striking comparisons of SOM classifications in various geologic settings to original amplitude data 
Paradise uses robust, non-linear machine learning technology to classify patterns in multiple attributes simultaneously, thereby extracting more information from the seismic response, even below classic seismic tuning. Use Paradise to:
Discover how Paradise can increase interpretation effectiveness, identify the extent of reservoirs more accurately, and evaluate leaseholds with confidence.
Test drive Paradise
What is Machine Learning?
Machine learning techniques apply algorithms that learn iteratively from the data and adapt independently to produce repeatable results. The goal is to address the big data problem of interpreting massive volumes of data while helping the interpreter better understand the interrelated relationships of different types of attributes contained within 3-D data. The technology classifies attributes by breaking data into what computer scientists call “objects” to accelerate the evaluation of large datasets and allow the interpreter to reach conclusions much faster.
Are you new to Paradise?
FEATURED RESOURCES
Machine Learning is changing the way interpretation is done. Find out how these geoscientists are using machine learning to reveal unprecedented levels of detail in seismic data.
Thin Beds and Anomaly Resolution in the Niobrara
Download PDF Identifying thin beds using machine learning In March of 2018, a study was conducted of the Niobrara ...
Read More
Read More
Significant Advancements in Seismic Reservoir Characterization with Machine Learning
Download PDF By: Rocky Roden and Patricia Santogrossi Published with permission: The First - SPE Norway Magazine Volume 3 September ...
Read More
Read More
Seismic Interpretation of DHI Characteristics with Machine Learning
Paradise International Webinar Presented by Rocky Roden The accurate interpretation of DHI characteristics has proven to significantly improve the ...
Read More
Read More
New Tools for Interpretation
Select an icon below to learn more about powerful, straightforward workflows in Paradise
PRINCIPAL COMPONENT ANALYSIS (PCA)
Identify attributes that have the greatest contribution to the region according to their relative variance
SELF-ORGANIZING MAP (SOM)
Probe, analyze, and understand classification results in the Universal Viewer to refine an interpretation
INTERACTIVE 2D COLORMAP
Run different SOM configurations to extract greater information from multiple attributes simultaneously
UNIVERSAL VIEWER
Display 2D and 3D views of data while using the 2D Colormap to gain understanding of classification results
GEOBODY ANALYSIS
Reveal the attributes that correspond to a geobody according to their relative contribution through the SOM process
“…machine learning software in Paradise is applied to seismic attributes to find patterns and important geology… [and] Self-Organizing Maps are used to analyze data at single sample resolution.”
— American Oil & Gas Reporter
Guided ThoughtFlowsTM
Paradise enables every interpreter to use powerful machine learning processes through straight forward, left-to-right guided workflows. Learn more about how to set up and generate a PCA chart of attributes and SOM classification results, then use the unique 2D Colormap with the 3D Viewer to interpret geobodies.
“Paradise distills a variety of information from many attributes simultaneously at single sample resolution… This is one of the many differences in the application of machine learning and pattern recognition methods available in Paradise.”
— GEO ExPro
Read case studies on the application of machine learning processes, including Self-Organizing Maps (SOM’s) and Principal Component Analysis (PCA), as applied to seismic attributes in various geologic settings, including onshore – conventional and unconventional – and offshore.