Supervised seismic facies classification using probabilistic neural networks: Which attributes should the interpreter use? Available to Purchase

In the last decade, machine learning algorithms such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Self-organizing Maps (SOM) have been adopted by geoscientists both to extract more detailed information and to accelerate the interpretation of their data. In this study, we present a novel technique called Exhaustive PNN which uses Probabilistic Neural Networks to determine the best suite of seismic attributes to perform a supervised seismic facies classification to differentiate salt from the background seismic response in a Eugene Island seismic survey, offshore Louisiana.

Presentation Date: Tuesday, September 17, 2019

Session Start Time: 8:30 AM

Presentation Time: 11:25 AM

Location: 221C

Presentation Type: Oral