Using Self Organizing Maps to Expose Direct Hydrocarbon Indicators

Using Self Organizing Maps to Expose Direct Hydrocarbon Indicators

Utilizing machine learning in Paradise to define and reveal features not seen in conventional interpretation in an offshore Gulf of Mexico oil/gas field. The SOM analyses using DHI characteristics and seismic attributes to reveal hydrocarbon contacts, amplify attenuation features and define ampliltude conformance in a Class 3 AVO.

Seismic Interpretation with Machine Learning

Seismic Interpretation with Machine Learning

Today’s seismic interpreters must deal with enormous amounts of information, or ‘Big Data’, including seismic gathers, regional 3D surveys with numerous processing versions, large populations of wells and associated data, and dozens if not hundreds of seismic attributes that routinely produce terabytes of data. Machine learning has evolved to handle Big Data. This incorporates the use of computer algorithms that iteratively learn from the data and independently adapt to produce reliable, repeatable results. Multi-attribute analyses employing principal component analysis (PCA) and self-organizing maps are components of a machine-learning interpretation workflow (Figure 1) that involves the selection of appropriate seismic attributes and the application of these attributes in an unsupervised neural network analysis, also known as a self-organizing map, or SOM.

Submitting....

X

What can we help you find today ?

More information about machine learning
More information about Paradise
More information on attributes
Identifying DHIs using SOM
Identifying thin beds / interpreting below tuning
Identifying geobodies using SOM
Something else...
Just looking around

Please tell us a bit about yourself so that we can provide the right information.

Your Role

Geoscience manager
Geophysicist
Geologist
IT
Senior Manager
G&G Technology
Other

And where you work in the industry?

E&P company
Consulting
Student
Technology / Equipment company
Other
X

Send Message