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.
Deborah Sacrey, Owner and Geophysicist of Auburn Energy, provides a review of the various attribute categories and their possible machine learning application to solve problems in seismic interpretation.
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.
Using multiple attributes to evaluate a 3D volume in offshore South America containing unexpected high pressure zone and the application of seismic attributes in a SOM to help define seismic facies and isolate the pressure zone.
Part 1 of a 2-part Paradise Application Brief series demonstrating better well planning, identifying more productive perforation intervals and aiding in the retention of critical leases while identifying good productivity areas and expose structure (karst), stratigraphy and rock properties (flat spots) in carbonates in the Viola via machine learning.