Data Analytics in Reservoir Engineering

Reservoir engineering is rapidly evolving, and traditional methods alone can no longer meet the demands of today’s complex reservoirs and business needs. In this course, you will learn how to leverage cutting-edge data analytics techniques to extract valuable insights from vast amounts of reservoir data.

In this course, we will explore current applications of data analytics in reservoir engineering, ensuring you develop a clear understanding of how these techniques can enhance your work. Additionally, we will delve into recent trends and developments that merge data-driven and physics-based methods (hybrid reservoir models), enabling you to stay ahead of the curve in this rapidly evolving field with focus on surveillance, reservoir management and field optimization for unconventional and conventional reservoirs.

From understanding the methodology behind model development to exploring machine learning algorithms, you’ll gain a solid foundation in data analytics and its relevance in reservoir engineering that will allow you to make more informed decisions and optimize reservoir performance.
We will guide you through a hands-on model development process, equipping you with the best practices and helping you navigate potential pitfalls. No prior Python knowledge is required, but we will provide optional code samples for those interested in diving deeper.
As we wrap up the course, we will explore future trends in data, models, automation, and the human element in reservoir engineering. You’ll gain valuable insights into where the industry is headed, ensuring you stay at the forefront of innovation.

Duration: 6 hours

What you will learn:

• Introduction to data analytics framework and methods
• Hands-on model development process, understand best practices and pitfalls
• Importance and relevance of data analytics in reservoir engineering
• Basic ideas and familiarity of current applications of data analytics in reservoir engineering
• Recent trends and developments in merging data-driven and physics-based methods

Pre-requisites

• Familiarity with traditional reservoir engineering methods (simulation, pressure/rate transient analysis, PVT, material balance, waterflood, etc.)
• Python knowledge is beneficial but not required. Course code samples will be using Python and are optional.