Dr. Carolan Laudon will be part of the 2022 Unconventional Resources Technology Conference
Dr. Carolan Laudon will be a keynote speaker at the Unconventional Resources Technology Conference (URTeC). URTeC continues to be one of the best opportunity to exchange information, formulate strategic ideas and solve problems to manage and optimize unconventional resource plays. Leveraging from all technical backgrounds and disciplines, URTeC is critical by delivering the science, technology, and commercial opportunities on what’s working with the current business environment.
Dr. Laudon’s presentation will be part of the Geophysical Reservoir Analysis Theme. Geophysics is an essential tool for measuring, diagnosing, and analyzing subsurface properties. The purpose of this theme is to highlight these methods and case studies of their results. In addition, a critical objective is to highlight the interaction with and integration into geological and engineering end products.
Visit the event website for the complete event schedule and registration information.
Please visit our Products page to learn more about the capabilities of the Paradise AI workbench used in this presentation.
Carolan Laudon holds a Ph.D. in Geophysics from the University of Minnesota and a B.S. in Geology from the University of Wisconsin Eau Claire. Carolan has worked as a Senior Geophysical Consultant with Geophysical Insights since 2017 applying the Paradise® machine learning workbench. Prior roles include Vice President of Consulting Services and Microseismic Technology for Global Geophysical Services and 17 years with Schlumberger in technical, management and sales roles. Her work with Schlumberger included offices in Alaska, Aberdeen, Scotland, Houston, TX, Denver, CO and Reading, England. Carolan spent the first five years after graduate school with ARCO Alaska in the exploration team as a seismic interpreter.
URTeC 2022 – Applying Machine Learning Technologies in the Niobrara Formation, DJ Basin, to Quickly Produce an
Integrated Structural and Stratigraphic Seismic Classification Volume Calibrated to Wells
Abstract by Carolan Laudon, Jie Qi, Yin-Kai Wang
Objectives/Scope: This study will demonstrate an automated machine learning approach for fault detection in a 3D seismic volume which combines Deep Learning Convolution Neural Networks (CNN) with AASPI pre and post processing to produce high quality fault attribute volumes of fault probability, fault dip magnitude and fault dip azimuth. These volumes are then combined with instantaneous attributes in an unsupervised machine learning classification which allows isolation of both structural and stratigraphic features into a single 3d volume. The workflow is illustrated on a 3d seismic volume from the Denver Julesburg Basin and a statistical analysis is used to calibrate results to well data.
Methods/Procedures/Process: Starting with an amplitude volume, the method has four steps. Pre-processing produces the volume used as input to CNN fault classification plus dip volumes used in post processing. Next, CNN applies a 3d synthetic fault engine to predict faults. Then, a Laplacian of Gaussian filter enhances faults in their primary direction and skeletonization produces skeletonized probability, dip and azimuth. The result is a higher quality when compared to the output from CNN alone (without pre and post processing). The fault volumes are next combined with instantaneous attributes in an unsupervised machine learning classification through Self-Organizing Maps (SOM) to produce a classification volume from which faults and reservoir neurons can be isolated, calibrated to wells and converted to geobodies.
Results/Observations/Conclusions: The results provide a rapid, robust and unbiased fault interpretation which can be used to create either fault plane or fault stick interpretation in a standard interpretation package. The SOM is preceded by principal component analysis to identify prominent attributes. These resolve the seismic character of the analysis interval (Top Niobrara to Top Greenhorn). In addition to enhanced fault identification, the Niobrara’s brittle chalk benches are easily distinguished from more ductile shale units and individual benches; A, B, and C each have unique sets of characteristics to isolate them in the volume. Extractions from SOM volumes at wells confirm the statistical relationships between SOM neurons and reservoir properties.
Applications/Significance/Novelty: Traditional seismic interpretation, including fault interpretation and stratigraphic horizon picking, is poorly suited to the demands of unconventional drilling with its typically high well densities. Geophysicists devote much of their efforts to well planning and working with the drilling team to land wells. Machine learning applied in seismic interpretation offers significant benefits by automating tedious
and somewhat routine tasks such as fault and reservoir interpretation. Automation reduces the fault interpretation time from days/weeks to hours. Multi-attribute analysis accelerates the process of high grading reservoir sweet spots with the 3d volume. Statistical measures make the task of calibrating the unsupervised classification results feasible.