About this Virtual Instructor Led Training (VILT)
The classical use of decline curve analysis across a reservoir’s life cycle is well documented. We have oil, gas, and water production data. Critical petrophysical data are interpreted from an array of well logs and cores. Shedding light on complex multidimensional and multivariate subsurface systems is vital to reduce re-engineering decision-cycles and optimize forecasting accuracy.
This Virtual Instructor-Led Training (VILT) will discuss key Machine Learning (ML) and Deep Learning (DL) techniques to help the reservoir engineer analyze the production time-series data to forecast well performance. Participants will explore and fully understand the difference between supervised and unsupervised learning and how to use the ML/DL algorithms under each learning technique.
By the end of this VILT course, you can immediately see the value by applying ML/DL on your upstream well data and fluids production. Are you someone in E&P who is interested in using Python to be a key member of your company’s digitalization project to optimize field production and employ data-driven forecasting techniques? This two half-day session will then get you going with sound background understanding, illustrated by real case studies. Some open-source Jupyter Notebooks will be shared with participants to start their journey towards accurate and reliable Forecasting.
This VILT course will equip participants with an understanding of:
- Fundamental concepts of Machine Learning and Deep Learning in Oil & Gas
- Machine Learning workflow and how to implement the steps effectively
- The role of performance metrics and how to identify their essential methods
- Upstream Case Studies with data and Python Notebooks to KO your practical application of ML/DL
This VILT course is designed for specifically for those involved with reservoir, completion, and production in operating and service companies. In general, those involved in planning, completion, and operation in assets are an essential target audience. Also, it will benefit oil and gas professionals interested in understanding how to apply machine learning methods in their upstream projects and traditional workflows and have some experience in using Python in Jupyter Notebooks.
This VILT will be delivered online in 2 half-day sessions comprising 4 hours per day, with two breaks of 10 minutes per day.
Course Duration: 2 half-day sessions, 4 hours per session (8 hours in total)
Your expert course leader has 14 years of experience in the Oil and Gas industry as a geophysicist processing and interpreting seismic data. More than 11 years of software development experience with SAS Institute, Inc., a leader in statistical software and analytics solutions. Ten years of upstream Oil and Gas data-driven model building across Exploration and Production. Currently developing business strategies to establish Analytical Centres of Excellence and data management architectures across the Oil and Gas industry.
Day 1 will shed light on the data-driven approaches and help participants decide when and how to get the most out of a digital transformation to optimize production forecasts.
Day 2 will get into the details of what was covered in Day 1. Participants will go through five anonymized case studies that implement time-series analysis to optimize production forecasting.
The Oil &Gas industry is late to the digital transformation but Day 2 will lift the veil on successful applications. Participants will see where operators have operationalized Machine Learning (ML) and Deep Learning (DL) for business value, enabling geoscientists to become data scientists and accelerate their insights for enhanced productivity.
Learn what past participants have said about PetroEdge training courses
I have known Mr. Keith Holdaway for many years. He is one of the best Domain Experts with solid understanding of AI and Machine Learning. I strongly recommend taking short courses that he teaches
Shahab D. Mohaghegh, Ph.D., CEO Intelligent Solutions Inc and Professor, Petroleum & Natural Gas Engineering, West Virginia University
This is a time of great change in the oil and gas industry, and even before embracing real time systems, we were struggling to extract meaningful insights from a large accumulation of data that was right under our noses. Based on his years of global experience, Keith has developed a deep technical understanding of these issues, and in his book, Harness Oil and Gas Big Data with Analytics, he combines this understanding with his unique talent for communicating complex issues in a straightforward manner