In this paper, authors suggest a workflow that enables interpreters to apply principal component analysis (PCA) and self- organizing maps (SOM) on the most appropriate mathematically independent seismic attributes to get one classification volume. The aim is to obtain one clustered volume that best shows all small faults affecting the area.
Recommended
Sharareh Manouchehri, Nam Pham, Terje A. Hellem and Rocky Roden predict lithofacies and reservoir properties using multi-attribute seismic analysis based on an unsupervised machine learning process called Self-Organizing Maps (SOMs).
A workflow is presented which includes data conditioning, finding the best combination of attributes for ML classification aided by Principal Component Analysis, unsupervised ML through SOM multi-attribute seismic sample training and then survey classification in the zone of interest and, finally, geobodies created from classified samples of selected winning neurons, Visualization of these results are outlined in this paper.
Published in the special Machine Learning edition of First Break, this paper lays out results from multi-attribute analysis using Paradise, the AI workbench.
Using a new supervised learning technique, convolutional neural networks (CNN), interpreters are approaching seismic facies classification in a revolutionary way as explained by Tao Zhao at SEG Anaheim (2018).
A glossary defining essential machine learning terms within the seismic interpretation and geoscience community from Principal Component Analysis (PCA) to Self-Organizing Maps (SOM) and everything in between.
Using machine learning to classify a 100-square-mile seismic volume in the Niobrara, geoscientists were able to interpret thin beds below seismic tuning and identify anomalies at resolutions not possible with traditional interpretation.
Machine Learning is a subset of Narrow AI that does pattern classification. It’s an engine – an algorithm that learns without explicit programming.