The application of machine learning to classify seismic attributes at single sample resolution is producing results that reveal more reservoir characterization information than is available from traditional interpretation methods.
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.
Using machine learning to analyze 5 instantaneous attributes helped reveal patterns across 5 instantaneous attributes and unique Eagle Ford facies.
Applying Principal Component Analysis (PCA) and Self-Organizing Map (SOM) process to show faults on the base amplitude seismic survey and faults using similarity attributes showing large variance.