Date/Time
Date(s) - 08/08/2024
11:30 am - 1:15 pm
Location
Wynkoop Brewing Company
Categories
If the PayPal option does not allow you to pay with credit card, you can pay with a card in person at the luncheon. Just use the Pay by Check option at checkout so we can get a good headcount.
Machine Learning for Lithofacies Prediction – a Fast, High-resolution, an Economic Alternative to Seismic Inversion.
A methodology for lithofacies prediction is presented. It is based on computing Self Organized Maps (SOM), an unsupervised form of Machine Learning (ML), and cross-referencing the results to lithofacies from petrophysical logs. The methodology defines the lithofacies of interest with improved resolution and significant time savings when compared to inversion-based reservoir characterization.
Methodology
Unlike seismic and petrophysical inversions, the proposed methodology is not deterministic. It computes SOM from a User defined number of seismic attributes. The process’ multi-dimensionality (each attribute is a dimension) reduces the non-uniqueness associated with seismic and petrophysical inversions. SOM classifies several attributes sample by sample (same sample for all attributes) and assigns a cluster (neuron) to each time/depth sample. This results in interpretable data below the wavelet’s limit of resolution.
The assignment of geologically meaningful labels to SOM neurons is done by cross-referencing neurons from seismic to lithofacies computed from the wells’ petrophysical evaluation. By matching neurons to lithofacies at the same depth, the process assigns a label to each neuron that indicates the most likely rock type. This way, we can use the SOM neurons to map the distribution and variation of the lithofacies in the subsurface.
The methodology does not require wavelet estimation or a low frequency model; thus, easing processing and interpretation requirements.
Case History
A case history in the Niobrara formation is presented to illustrate the methodology (Chaveste et al, 2023). The petrophysical evaluations in five wells are used to create four lithofacies. The lithofacies, computed using K-Means, are cross-referenced with a 64 neuron SOM in which eight seismic attributes are input to the calculation. The result is a 3D volume of lithofacies that matches the analysis wells, has aerial continuity, shows reliable data at a fraction of the wavelet’s limit of resolution, and provides a value of probability of occurrence at each seismic sample.
Bio – Michael A. Dunn
In January 2017 Michael Dunn joined Geophysical Insights as Sr. Vice President of Business Development. In this role, Mike assumes the leadership responsibility for the company’s global business development. As a part of this role Mike will also be heavily involved in Geophysical Insight’s technology and software development.
Mike has a wealth of experience in the oil and gas industry. He started his career as a geophysicist at Shell Oil Company where he held technical and managerial roles in both operations and research. In the late 1990’s Mike left Shell and founded, with other partners, Geokinetics, a full service geophysical company. Under his leadership in various executive positions Geokinetics grew significantly culminating in a public offering on the American Exchange in 2007.
In 2009 Mike became Vice President of Technology for Woodside (USA) where he directed the company’s technology strategy to increase valuation of their exploration portfolio and production assets. He continued in this role until 2013 when Woodside consolidating its operations to Australia . In that same year, he joined Halliburton where he served as Sr. Director of Geology, Geophysics and Reservoir Engineering. Under his leadership, the portfolio was significantly augmented and redirected.
Mike has a Bachelor’s degree in Geology from Rutgers University and a Master’s degree in Geophysics from the University of Chicago. He attended Shell executive training programs at MIT’s Sloan School of Business Management and the University of Houston’s Bauer School of Business.
Doors open at 11:30 am. Meeting and presentation starts at 12 pm.
Bookings
Bookings are closed for this event.