From Data Gathering, Critical Statistics to Predictive Modelling: Execution Steps of a Data Science Project Applied to Oil and Gas
This one-day course will teach the fundamentals of data science project design and execution, including data collection principles and statistics through Design of Experiments (DOE). By engaging participants in hands on, dynamic experiments covering data collection, model selection, model assessment, simulation and forecasting; students will gain a foundational understanding of the key principles of the analytics project life cycle. The physical and collaborative nature of this experience will ingrain a tangible, unforgettable understanding of the critical concepts that successful analytics projects require.
Exposure to advanced statistics, Design of Experiments and Machine Learning concepts will be covered in this course. This course will provide an engaging experience for the class participants with hands on, dynamic experiments covering data collection, model selection, model assessment, simulation and forecasting; students will gain a foundational understanding of the key principles of the analytics project life cycle.
Topics covered include:
- Review of Advanced Statistics Concepts
- Measurement System Analysis
- Design of Experiments (DOE)
- Analysis of DOE
- Hands on R Working Sessions
- Live Simulation of concepts using Catapults
- Machine Learning applying select algorithms
Introductory to Intermediate
- Every technical person associated with Oil and Gas operations should take this course.
- It is very expensive to experiment with Oil and Gas processing and subsurface systems. Most oil and gas systems are very complex and it is very difficult to determine is if a process/production /well bore design change has had a positive, or detrimental effect. The time to demonstrate results is very lengthy. Other producers have found that it takes us 9 to 12 months to test a new well design and the determination of how effective it performed.
- Process/Production engineers often have a difficult time determining how well a processing change has had on production, or feed quality due to multiple variables constantly changing within the system.
- DoE is an efficient way to obtain the maximum amount of information with the least amount of experimental runs – by testing more than one variable at a time. The time required to determine an optimal well design can be compressed from years to months.
- In addition, some selected Machine Learning concepts will also be applied in this hands on course
Technical Managers, Technical Staff involved with: Subsurface Analysis/Design, Production and Large Facility Process Optimization.
.8 CEUs (Continuing Education Units) are awarded for this 1-day course.
- Attendees will need to bring their laptops, with R v3.6, or higher and R Studio preloaded and working prior to this course.
- Attendees will need to preload some specific R packages prior to this course and they need to confirm that they are working properly.
- Attendees need to bring relevant designs/problems to use for in-class discussion.
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.
Peter Dimmell has over 22 years of Oil and Gas experience working with Oilsands, SAGD, Refining, Oil and Gas E&P companies as follows: Suncor, Royal Dutch Shell, Husky, Cenovus, Encana, Crescent Point, and Northwest Redwater Refinery. The last 12 years have been focused on delivering high value Advanced Analytics Projects and implementing predictive models for: Drilling, Completions, Reservoir G&G, Production Engineering, Operations, Reliability/Maintenance, Supply Chain, Strategic Planning. Peter has Masters in Civil Engineering and Earth Sciences from Waterloo. Peter has taught these concepts to Oil and Gas Professionals since 2008.