Dr. Tom Smith presents “Geobodies in Paradise: a Machine Learning Application” at the 2018 SEG Convention in Anaheim, California. Dr. Smith explains four geobody examples including Golden 3D Survey Geobodies, Eagle Ford Sweet Spot Predictions, Niobrara Sweet Spot Predictions and Stratton Field Strategraphic Fabric by Geobody Shape Classification.
Solving Interpretation Problems using Machine Learning on Multi-Attribute, Sample-Based Seismic Data
Deborah Sacrey of Auburn Energy hosts a webinar addressing challenges like interpretation of thin bedded reservoirs far below conventional seismic tuning and more using Paradise®, machine learning software for seismic interpretation.
Machine Learning for Seismic Interpretation driven by the nature of the technical and business demands facing geoscientists as oil and gas activity is advancing a new phase of unconventional reservoir development in an economic environment that rewards efficiency and risk mitigation.
This paper sets out a unified mathematical framework for the process from seismic samples to geobodies.
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.