Geologic Pattern Recognition from Seismic Attributes: Principal Component Analysis and Self-Organizing Maps
Current computing technology has allowed for the application of new machine learning techniques in analyzing seismic data through pattern recognition methods such as Self-Organizing Maps in Paradise.
Seismic attributes identify many geologic features in seismic data where PCA helps identify optimal attributes and help determine which attributes to use in a multi-attribute analysis using SOM. The process in Paradise reveals natural clustering by pattern recognition in the data helping define aspects like stratigraphy, seismic facies, DHI features and sweet spots for shale.
Risks and rewards are evenly poised in the hydrocarbons industry, and along with oil and gas companies, probably no one understands the nuances better than Tom Smith, founder and president of Geophysical Insights.
New technology for the Big Data problem of the seismic volume using Unsupervised Neural Networks for the interpretation of Greenfield projects in a modular, affordable platform.