Artificial Intelligence Techniques, Strategies and Case Histories for the Petroleum Engineer

Disciplines
Engineering
Category
Foundational • Data Analytics • Production • Reservoir Characterization • Operations • Mapping
Format
Classroom • Live Online 
Available
Public • Private 

Who Should Attend

Experienced oil and gas professionals that are interested in applying alternative approaches to physics-based modeling and problem solving. Participants will learn about cases in which an AI approach to Petroleum Engineering problems has provided quick answers, offered a fresh perspective, quantify completion/frac design, reservoir, geology, chemistry, operations and other factors on well production and recovery. This course is intended for the experienced professional charged with solution development, reservoir assessment, completion design, hydraulic fracture assessment, prospect evaluation, recompletion candidate selection, or forecasting outcomes such as sand-outs, well production, recovery, etc. Potential participants include engineers, geologists, geophysicists, managers, data scientists, technicians, chemists, etc. Participants in this class will obtain the knowledge and expertise needed to identify potential applications for an AI approach to problem solving and the requirements needed for the AI approach. Programming skills are not required for successful completion of this course.

Description

Participants will learn the fundamentals of using AI techniques to solve problems. In addition, actual Petroleum Engineering case histories will be presented and there will be discussion to help participants understand why an AI approach was used in these instances. The AI approach in these case histories resulted in better reservoir understanding, significant cost savings and/or higher well production/recovery.

Although this is not a programming course, proficiency with Excel is helpful.

Learning Outcomes

  • Basic understanding of artificial neural network (ANN) modeling concepts.
  • Identify potential applications for an AI modeling approach.
  • Model development strategies to address specific needs or problems.
  • Techniques to mitigate real world uncertainty in data.
  • Strategies to minimize the impact of data issues such as quantity, quality, completeness, and consistency.

Course Content

AI Concepts and Theory

 

  • Predictive Model Development
    • Feed Forward Neural Network (ANN)
      • Model Training and Fitness
      • Predictor Evaluation, Genetic Algorithms
      • Model Selection
      • Use of Testing Data
      • Strategies and Application
      • Model Development Experiments
    • Self-Organizing Mapping
      • Model Training
      • Strategies and Application

    AI Case Histories

    • Evaluate Completion and Frac Design, Granite Wash Case; SPE-39814
      • Double Well Production for Lower Cost
    • Completion Design Evaluation, Marcellus Case; SPE 171003
      • Facilitate Increasing PUD Recovery to 10 BCF/Well
    • Evaluate Reservoir Proxy Data, Bakken Case; URTeC-2667653
      • Use Measurements Taken During Horizontal Drilling Operations as Proxies for Reservoir Quality
    • Predicting Sand-Outs, Mission Canyon Case; SPE 19191
      • Predict Frac Treatment Sand-Out to improve Operational Efficiency
    • Reservoir Classification, Wolfcamp B Case; SPE-210383
      • Evaluate the Usefulness of Reservoir Characteristics

In-Person

Length
1 Day

Upcoming Events

Houston

Instructor

Robert F. Shelley, PE headshotRobert F. Shelley, PE