An ongoing challenge to seismic interpreters is to identify and extract heterogeneous seismic facies on data volumes that are continually increasing in size. Geometric, geomechanical, and spectral attributes help to extract key features but add to the number of data volumes to be examined. Common interactive analysis tools include crossplotting, interactive animation, and 3D corendering where we examine more than one attribute at a time. When there are more than three attributes, principal component analysis, independent component analysis, self-organizing maps, and generative topographic mapping mathematically reduce the dimensionality of the data to a more manageable subset. Corendering different components and mapping against a 2D colorbar provides a means of user defined clustering, similar to that provided by k-means. The result of such unsupervised clustering is the identification of color-coded voxels that have similar expressions. Although data reduction and clustering techniques extract important patterns across attribute volumes, the interpretation of these patterns is the same as traditional interactive interpretation, where the interpreters integrate their geologic understanding of the depositional environment and tectonic deformation with well control to map areas that are more prospective or pose drilling hazards. In contrast, supervised classification such as Bayesian classification, probabilistic neural networks, and convolutional neural networks provides a statistical estimate of how likely any given voxel corresponds to one or more interpreter provided “labels”. Labels may include interpreter-painted seismic facies, hand-picked faults, or attribute vectors extracted about different facies, drilling problems, or fluid flow encountered by well bores. For both supervised and unsupervised machine learning analysis the interpreter can improve the results by using their understanding of the geology to provide a judicious choice of inputs and training data.
A novel part of the course is a hands-on component to compute attributes and seismic facies using software developed by the Attribute Assisted Seismic Processing and Interpretation (AASPI) consortium. Supplied data volumes are limited to those that are publicly available. However, participants will be able use a copy of the software for an additional three months at home or in their workplace to allow them to continue learning and identify which workflows provide useful results for their own non-publicly available data.
Duration
16 hours
Intended Audience
Intermediate
Prerequisites (Knowledge/Experience/Education required)
Advanced knowledge of seismic theory is not required; this course focuses on understanding and practice.
Course Objectives
After completion of this course, the participant will be able to:
- Compute state-of-the art seismic attributes on their own 3D data volumes.
- Use modern machine learning algorithms to multiple attribute volumes to better identify seismic facies on large 3D volumes
- Apply modern post-migration data conditioning algorithms to improve the quality of seismic amplitude data and subsequent attribute volumes.
- Through case studies and examples, recognize the seismic and attribute expression of common carbonate, clastic, igneous, and diapiric geologic features.
- By learning what the attributes measure, avoid common interpretation pitfalls and avoid overinterpreting volumes exhibiting marginal seismic data quality.
Teaching Methodology
The geophysicist of 2025 is overwhelmed by new technology. Most interpreters prefer to evaluate new technology by first applying it to data to see what happens. If they find the results to be interesting, they are then willing to invest the time to learn a little theory about a given technique works. I have structured this hybrid course to address this mode of learning. We will interleave two-hour sessions of traditional lectures emphasizing case studies, best practices, and pitfalls with two-hour sessions of hands-on application. Obviously, longer running applications can run during the lecture period, over lunch hour and coffee breaks, and even overnight. I will use the AASPI software (described in great detail under https://ou.edu/mcee/labs/aaspi/documentation) developed over the past 18 years at the University of Oklahoma, University of Alabama, SISMO, and the University of Texas, Permian Basin. This software currently runs in the Petrobras environment.
We fully expect the results of a previous session to spur further discussion, potential workflows, alternative geological interpretations, and questions about alternative methods. The instructors are therefore prepared to modify the presentation part of the course to address these issues.
Who should attend?
This course is designed for:
- Seismic interpreters who want to extract more information from their data.
- Seismic processors and imagers who want to learn how their efforts impact subtle stratigraphic and fracture plays.
- Sedimentologists, stratigraphers, and structural geologists who use large 3D seismic volumes to interpret their plays within a regional, basin-wide context.
- Reservoir engineers whose work is based on detailed 3D reservoir models and whose data are used to calibrate indirect measures of reservoir permeability.
Advanced knowledge of seismic theory is not required; this course focuses on understanding and practice.
