Online Live Streaming Course
5 sessions ( approx. 4 hours each) , August 5 to 8, 2024
Duration : 16 hours
WHO SHOULD ATTEND: Production, reservoir, completion, drilling and facilities engineers, analysts, and operators who want to enhance their knowledge base, increase technology awareness, and improve the facility with different data analysis techniques applied on large data sets.
OBJECTIVES:
In this hands-on course, the participants learn some data analysis and data science techniques and workflows applied to petroleum production (specifically artificial lift) while reviewing code and practicing. The main aim is to provide insight and understanding of data analytics and machine learning principles through applications. Field data is used to explain data-analysis workflows. Using easy to follow solution scripts, the participants will assess and extract value from the data sets. Hands-on solution approach will give them confidence to try out applicable techniques on data from their field assets.
PREREQUISITES
• Understanding of petroleum production concepts
• Knowledge of Python is not a must, but preferred to get the full benefit
• We will use the Google Collaboratory environment available in Google-Cloud for hands-on exercises
• Trainees will need to bring a computer with a Google Chrome browser and a Google email account (available for free)
BENEFITS:
• Understand data workflows for production applications
• Learn to extract value from field data for artificial lift applications
• Apply provided scripts on example and own field problems to solve leading edge production and artificial lift problems
Course content includes:
1. Digital Oil Field Data Explorations/Workflows
1.1. Digital Transformation and Oilfields
1.2. Key technologies for digital oilfields
1.3. Oilfield System Data Verification and Management
2. . A Brief/Incomplete Primer on ML/AI
2.1. Data Science versus Data Analytics
2.2. AI, ML and Deep Learning
2.3. Data Analytics Lifecycle
2.4. Bias-Variance-Complexity Tradeoff
2.5. Data Preparation
2.6. Model Types
2.7. Role of Domain Knowledge
2.8. Training & Evaluating Model
2.9. Toolsets
3. System Setup & Checks
3.1. Google CoLab – Why do we need it?
3.2. Pull datasets & codebase from the GitHub repository
4. Data workflows & Best Practices in Data Exploratory analysis –
4.1. Data types in Production Domain: Streaming (Real-time or time-series) vs. Static (non-streaming)
4.2. Data Processing Challenges
4.3. Data Basics: Cleaning, filtration, and regulation
4.4. Best practices on data exploratory analysis
5. Rod Pump Dynamometer Card Classification
Provide a brief description of the data set/problem use case and expected outcome
5.1. The problem, input, and output variables definition – SPE paper
5.2. Data set
5.3. Hands On Exercise: Model development & testing
6. Flow Pattern Prediction
Provide a brief description of the data set/problem use case and expected outcome
6.1. Problem, input, and output variables definition
6.2. Data set
6.3. Hands On Exercise: Model development & testing
7. Gas Lift Slugging
Provide a brief description of the data set/problem use case and expected outcome
7.1. Problem, input & output variables
7.2. Hands On Exercise: Regression Solution
8. Choke Flow Rate Study
Provide a brief description of the data set/problem use case and expected outcome
8.1. Problem, input & output variables
8.2. Hands On Exercise: Multiple ML models & comparison
9. Multiphase Flow Meter
Provide a brief description of the data set/problem use case and expected outcome
9.1. Problem, input & output variables – SPE Paper
9.2. Hands On Exercise: Multiple ML models & comparison
10. Virtual Flow Meter with ESP Data set (time permitting)
10.1. The problem, dataset – input/outputs
10.2. Two- or three ML solutions
