Application of Machine Learning in the Unconventional Tight/Shale Reservoir Development
Machine learning has been successfully used in various engineering disciplines. Nowadays, large amount of data related to reservoir properties, drilling, completion, and production is routinely collected in the upstream oil and gas operation, which can be further analyzed to optimize the field operations and improve the reservoir performance. This course starts with the basic Machine Learning concepts, application workflows and the supervised and unsupervised learning algorithms. The commonly used algorithms in both categories such as Clustering, Artificial Neural Networks, Decision Trees, Support Vector Machine will be presented, allowing participants to reach a clear understanding on their strengths. Specific examples will be discussed to demonstrate the application of each algorithm in the development of unconventional tight/shale reservoirs. The course is devoted to field applications of this technology with a focus on reservoir characterization, production analysis and prediction, and recovery enhancement.
- Introduction of Machine Learning concepts
- A typical workflow to design and develop a Machine Learning project
- Feature selection
- Supervised learning algorithms
- Unsupervised learning algorithms
- Machine learning applications in the reservoir characterization in tight/shale formations
- Machine learning applications in productivity prediction and recovery enhancement in tight/shale reservoirs
Upon completion of this course, participants are expected to have a good understanding of the characteristics of the machine learning approaches and be able to use them to identify potential application domains in the upstream oil and gas industry. They will acquire detailed knowledge of the popularly used machine learning algorithms and the workflow to employ these algorithms to solve petroleum engineering problems. Finally, they will see the demonstrations of different machine learning algorithms to reservoir characterization, production analysis, well productivity forcast, and recovery enhancement in tight/shale reservoirs.
Introductory to Intermediate
In the upstream oil and gas operations, only 1 trillionth of the subsurface data is likely to be directly sampled, meanwhile the data collected can be very diverse in terms of types and scales. Thus, it is very challenging to apply machine learning approaches to solve the practical problems in the complex upstream oil and gas environment. This course will focus on the machine learning applications in the unconventional tight/shale reservoir development, such as reservoir characterization, production analysis, completion optimization and well after-stimulation production forcast. In particular, the reservoir engineering knowledge is repeatedly referred to when interpreting the results of the machine learning approaches.
This course is designed for managers and engineers from early career to senior in oil & gas companies or service companies. Those who are involved with drilling, reservoir, completion, and production in the unconventional tight/shale reservoirs are the main target audience.
.8 CEUs (Continuing Education Units) are awarded for this 1-day course.
All cancellations must be received no later than 14 days prior to the course start date. Cancellations made after the 14-day window will not be refunded. Refunds will not be given due to no show situations.
Training sessions attached to SPE conferences and workshops follow the cancellation policies stated on the event information page. Please check that page for specific cancellation information.
SPE reserves the right to cancel or re-schedule courses at will. Notification of changes will be made as quickly as possible; please keep this in mind when arranging travel, as SPE is not responsible for any fees charged for cancelling or changing travel arrangements.
We reserve the right to substitute course instructors as necessary.
Dr. Shengnan (Nancy) Chen is currently an Associate Professor in the Department of Chemical and Petroleum Engineering, at University of Calgary. Her research area focuses on the development of unconventional tight and shale reservoirs with multistage hydraulic fractures, aiming to maximize the hydrocarbon recovery while minimizing the water usage and footprints. In recent years, she is devoted to combine the data mining/machine learning methods with the reservoir engineering knowledge to optimize the field operations in the tight/shale formations in Western Canada. Dr. Chen has authored and coauthored over 60 journal and conference papers. She won the SPE Canadian Distinguished Achievement Award for Petroleum Engineering Faculty in 2019.