Application of Digital Hybrid Tools That Combine Analytics, Machine Learning & Reduced Physics Models to Increase Oil Recovery in Mature Conventional Fields
Disciplines: Data Science and Engineering Analytics | Reservoir
Course Description
Conventional mature fields spread across the world – USA, Russia, Canada, Middle East, North Africa, South America and Southeast Asia, contribute to as much as 70% of all world’s oil. The cheapest and the quickest way to add oil is to increase from existing producing fields. Accordingly, the current challenges to meet world energy needs have increased focus on conventional mature fields. These fields are characterized by the availability of data and hence, lend themselves well to use of new digital tools to identify using unique workflows opportunities to increase oil production.
The democratization of advanced algorithms and the availability of data in conventional mature fields lend themselves well to their adoption of new subsurface workflows. These new workflows aided by digital tools can drastically improve decision making on improving recovery by no CAPEX expenditures (redistributing water/gas/chemicals being injected amongst current wells) or identifying where next to drill the injection or production well.
Digital tools that use these advanced algorithms can be a key differentiator and organizations are already unlocking higher recoveries from existing fields. The availability of data and democratization of these advanced algorithms is changing the landscape of subsurface workflows – helping create as well as improve existing ones. We are in an exciting phase in the industry where access as well as ease of using these advanced tools is transforming decision making in organizations.
In this course, we will start by reviewing new modeling techniques – analytics, machine learning, reduced physics and their applicability in determining relationships. We will showcase how each of these tools and techniques have been successfully applied to field data. Using successful deployment case studies, we show how combination of these tools help create hybrid models that address shortcomings associated with individual approaches We will focus on two specific applications – optimizing injection operations in conventional mature fields (gas injection, water injection or polymer/surfactant injection) as well as opportunities to accelerate field development planning for brownfields as well as greenfields.
Topics
- Review of data mining techniques, machine learning and reduced physics along with hands on sessions on how to access them easily over open-source platforms - Python and Google’s Tensor Flow.
- Constructing hybrid models that combine different models – the shortcomings of using individual approaches versus the hybrid approach and hands on sessions explaining the same using field data.
- Application of digital hybrid tools to specific subsurface data and the successful implementation that lead to optimization/decision making for current producing fields.
- Successful case studies of hybrid models to optimize water and/or gas injection operations in conventional fields by application of these digital hybrid tools
- Successful case studies that demonstrate integration of these advanced modeling tools with existing workflows of reservoir simulation to accelerate field development planning
Learning Level
Intermediate to Advanced
Course Length
1-day
Why Attend
We are constantly seeking ways to use advanced algorithms using subsurface data in the E&P industry. The easy access to advanced algorithms at great computational speeds has democratized modeling. While we now have a working understanding of these advanced algorithms, they also have their shortcomings when it comes to adapting them to field data. While current digitization efforts have focused efforts on getting data in one place (critical step), the real ROI can come by use of this data in unique workflows for our decision making.. Accordingly, the use of these digital tools in a hybrid manner helps creating unique workflows to accelerate decision making.
This will be a great competitive advantage to organizations that are seeking application of advanced algorithms to increase recovery from mature conventional fields. Take this course to understand how to apply these tools and techniques to subsurface data and equip your team and yourself with skills that is transforming the E&P business in the coming years.
Who Attends
This course is designed for subsurface engineers and managers responsible for field development planning as well as optimizing existing operations. Specifically, those involved with reservoir, petrophysics and production engineering roles in operating as well as service companies will find the course beneficial. Engineers working in newly founded data science teams in oil and gas companies will especially find inspiration from different case studies. Data science engineers will also find the distinction between models and a framework for hybrid model workflows greatly beneficial.
CEUs
0.8 CEUs (Continuing Education Units) are awarded for this 1-day course.
Cancellation Policy
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.
Instructor
Other courses by this instructor
Ashwin Venkatraman
Advanced analytics and ML algorithms are transforming subsurface decision making in the oil and gas industry. The democratization of analytical tools is seeing historical data being analyzed more routinely than was done earlier. This is helping acceler...
(Read More)Disciplines: Data Science and Engineering Analytics | Drilling | Management
Ashwin Venkatraman
Machine learning (ML) algorithms are transforming workflows in the oil and gas industry. The democratization and access to advanced computational tools is helping organizations exponentially accelerate their decision making using these powerful tools. ...
(Read More)Disciplines: Completions | Data Science and Engineering Analytics | Drilling | Management | Production and Operations | Projects, Facilities, and Construction | Reservoir
Ashwin Venkatraman
Data driven modeling is becoming a key differentiation to unlock higher recoveries from existing fields as well as identify new opportunities. The availability of data and democratization of these advanced algorithms is changing the landscape of subsur...
(Read More)Disciplines: Data Science and Engineering Analytics | Drilling | Production and Operations | Reservoir