Dr. Tom Smith presenting on Machine Learning at the 3D Seismic Symposium on March 6th in Denver
What is the "holy grail" of Machine Learning in seismic interpretation? by Dr. Tom Smith, GSH Luncheon 2018
Using Attributes to Interpret the Environment of Deposition - A Video Course. Taught by Kurt Marfurt, Rocky Roden, and ChingWen Chen
Dr. Kurt Marfurt and Dr. Tom Smith featured in the July edition of AOGR on Machine Learning and Multi-Attribute Analysis
Rocky Roden and Ching Wen Chen in May edition of First Break - Interpretation of DHI Characteristics using Machine Learning

Patricia Santogrossi speaks at the Houston Geological Society Northsiders' Luncheon

Tuesday, March 15, 2016
Southwestern Energy

10000 Energy Dr. Houston TX
Social 11:15 AM, Luncheon 11:30 AM
Cost: $30 pre-registered members; $40 for non-members/ ALL walk-ups (Credit Cards Now Accepted);
$25 for Emeritus/Life/Honorary; $10 for students if pre-registered and pre-paid.

To guarantee a seat, you must pre-register on the HGS website and pre-pay with a credit card.  You may walk up and pay at the door if extra seats are available.  Please cancel by phone or email within 24 hours before the event for a refund.  Online & pre-registration closes Tuesday, March 15, at 5:00 a.m.


If you are an active or associate member who is unemployed and would like to attend HGS meetings, please call the office for a discounted price. We are looking for one extra member to volunteer at the registration desk as well.




Speaker:  Patricia Santogrossi
Geophysical Insights

Encore Presentation

Sub-seismic Resolution in the Eagle Ford Enabled by Multi-Attribute Analysis in Paradise: Instantaneous, Geometric, and Spectral Decomposition Self Organizing Maps

These days many unconventional plays are being challenged by the low commodity price.  During market downturns, many operators look for ways to “squeeze” more information out of their seismic and well control data to reduce risk of a dry hole or a poorly performing well.

The Paradise® geoscience analysis platform is a triple threat.  First, we employ Principal Component Analysis (PCA) to identify and quantify the key attributes of any given class that are the most independent and characteristic in the data set. Usually a dozen or fewer attributes rise to the top and can be included in a Self-Organizing Map (SOM) wherein the learning machine classifies the data by neurons which may reveal natural clusters, form discernible geobodies, and enable specific calibrations or correlations. The third weapon in the arsenal is an interactive 2D ColorMap that can be queried and inverted to “extract” the natural clusters or geobodies from the “forest.”

The conclusions to date in this study allow simple distinction of all of the members of the Eagle Ford (EF):  Upper EF (marl), Top EF Ash beds, and Basal Clay-rich shale. The Eagle Ford Shale target facies previously characterized as High Resistivity and Low Resistivity can now be shown to comprise four or more non layer-cake zones, to include one or more previously unrecognized and possibly underdeveloped (?) sweet spots, and to be offset by numerous faults, some of which are compressional.  Spectral Decomposition appears to reveal more in the overlying Austin Chalk and the underlying Buda than in the Eagle Ford.

These methods can be shown to enable an interpreter to prognose and calibrate wells better, to enhance an engineer’s precision in geo-steering, and to improve one’s confidence in leasehold evaluation.

Helpful Links: https://www.hgs.org/civicrm/event/info?reset=1&id=1637