20201029 Innovative Machine Learning Approach at Unconventional Production Prediction: The Type-Curve Optimizing Geostatistical Array (TOGA)

20201029 Innovative Machine Learning Approach at Unconventional Production Prediction: The Type-Curve Optimizing Geostatistical Array (TOGA)

Data Analytics
←  SPE - Calgary Section

Data Analytics Presents:
Innovative Machine Learning Approach at Unconventional Production Prediction: The Type-Curve Optimizing Geostatistical Array (TOGA)

Date: Thursday October 29th, 2020
Speaker: Dr. Shane Prochnow PG, Digital Geologic Advisor, Chevron ETC
Location: Webinar
A link will be emailed to your preferred address to you the day of the event 
Time: 12:00 PM - 1:00 PM 
Cost:
SPE Member: Free Non- Member: $20
 


Abstract:

Several years ago Chevron introduced an innovative data analytic workflow called the Type-Curve Optimizing Geostatistical Array (TOGA). TOGA ties unconventional reservoir and well completion characteristics to historical production and makes robust predictions of well performance. TOGA is built on a foundational geologic framework and leverages random forest machine learning optimized for subsurface data sets. Random forest methods are preferred for unconventional systems because they capture complex, multidimensional and non-linear interactions in noisy databases. TOGA is part of a portfolio of other machine learning and physically-based reservoir engineering tools used by Chevron to reduce uncertainty in unconventional reservoir performance prediction. The workflow generates performance prediction maps by applying the random forest multivariate relationships to grids of the key reservoir predictor variables.

These production prediction maps are stacked to form an array of locations that each have a unique expected production profile through time. TOGA output may be used to calibrate existing type curve workflows, define reservoir sweet spots, establish reservoir continuity, and predict ultimate recovery. Data science and machine learning approaches have progressed Chevron’s understanding of its assets, especially in the Permian Basin. Unconventional plays were once thought to be relatively unpredictable, highly variable, and having little connection to reservoir properties. TOGA and other proprietary data analytic technologies have enabled the identification of key reservoir performance drivers for each unconventional target zone under development.


Speaker Bio:


Dr. Shane Prochnow,
PG is a digital geologic adviser with Chevrons Technology Center’s Subsurface Digital Laboratory. Prochnow earned his BS, MS, Ph.D. and a three-year post-doctoral research opportunity with Baylor University at Waco, Texas focusing on the confluence of geology, earth surface processes, and computational modeling. Prochnow supplemented his educational experiences by teaching geospatial and geodetic sciences at Baylor University and other local technical colleges and serving as a reserve military officer. Prochnow has since spent 15 years in industry, first with ExxonMobil and then with Chevron Corporation. His research interests include unconventionals, reservoir characterization, geostatistics, machine learning, and integrating complex systems. Prochnow has published numerous peer reviewed papers and abstracts on a myriad of scientific and archaeological topics. He also has seven patents in process involving the application of machine learning and spatial statistics for oilfield applications.


Don't miss out and sign up today!



Is your Membership up-to-date? Are you looking to become an SPE Member? Learn more here!

​​​​​


October 29, 2020
From 12:00 PM to 1:00 PM
WEBINAR
Login