Online Live Streaming Course

July 14 10 18, 2025

Duration : 20 hours

Course Overview

This 5-day course is designed to equip reservoir engineers with the knowledge and skills to apply

Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL) to solve real-world challenges in conventional and unconventional reservoirs. Participants will learn how to extract actionable insights from data, optimize reservoir performance, and drive business value.

The course employs an intensive, hands-on learning approach that combines theoretical foundations with practical implementation, real-world case studies, and collaborative learning. The curriculum follows a strategic ‘building blocks’ progression through four key phases:

1. Foundation Phase establishes core AI concepts and data fundamentals with initial development environment setup.
2. Technical Development Phase advances into hands-on ML/DL/RL model building using industrial datasets
3. Advanced Implementation Phase focuses on real-time processing and systems integration
4. Integration and Application Phase culminates in a capstone project for implementing a functional upstream solution.

Throughout the program, participants will work with opensource (Python) development tools, real- world datasets, template code, and implementation frameworks, ensuring they gain practical experience that can be immediately applied in their organizations while receiving expert guidance and feedback at each stage.

Key Course Objectives and Outcomes

• Understand the fundamentals of data science, ML, and AI in the context of reservoir engineering.
  • Learn how to preprocess, analyze, and visualize reservoir data.
  • Apply ML and AI techniques to solve problems such as production forecasting, reservoir characterization, and anomaly detection.
  • Gain hands-on experience with Python, popular ML libraries (e.g., scikit-learn, TensorFlow), and reservoir simulation tools.
  • Develop strategies to integrate data-driven insights into business decision-making.
  •  

Who Should Attend this Course

This course is designed for the following professionals in the oil and gas sector:

• Oil and Gas industry professionals seeking to transition into digital transformation roles
• Data scientists and ML engineers working in the E&P value chain
• Reservoir engineers looking to gain insights from subsurface data to optimize production
• Technical managers overseeing digital transformation initiatives

Prerequisites for attending this course, participants should have the following:

• Basic understanding of reservoir engineering concepts
• Elementary knowledge of Python programming language
• No prior experience of data analysis and statistics

By the end of the course, participants will have the skills and confidence to leverage data science, ML, and AI techniques to solve complex reservoir engineering problems and drive business value in both conventional and unconventional reservoirs

Course Outline

Day 1: Introduction to AI concepts (4 hours)

Module 1: Introduction to Data Science and AI technologies in reservoir engineering

• Introduction to data science, AI, ML, DL, and RL
  • Applications in conventional and unconventional reservoirs
  • Business value of data-driven decision-making

Module 2: Python Basics for Reservoir Engineers

• Python programming fundamentals
  • Data manipulation with Pandas and NumPy
  • Data visualization with Matplotlib and Seaborn

Module 3: Reservoir Data Preprocessing

• Data cleaning and handling missing values
  • Feature engineering for reservoir data
  • Normalization and scaling

Module 4: Hands-On Exercise

• Loading and exploring a reservoir dataset
  • Preprocessing and visualizing well production data

Day 2: Exploratory Data Analysis (EDA) and Reservoir Characterization (4 hours) Module 5: Exploratory Data Analysis (EDA)

• Statistical analysis of reservoir data
  • Identifying trends, patterns, and outliers

Module 6: Reservoir Characterization Using Data Science

• Clustering techniques for rock typing and facies classification
  • Dimensionality reduction (PCA, t-SNE)

Module 7: Feature Engineering for E&P Datasets

• Extracting relevant features for asset monitoring and prediction
• Domain-specific features in reservoirs: Fiber optics (DTS and DAS)

Module 8: Hands-On Exercise & Case Study

• Performing EDA on well log data
  • Applying clustering algorithms to classify reservoir facies
  • Reservoir characterization in an unconventional shale play

Day 3: Machine Learning for Production Forecasting and Optimization Module 9: Introduction to Machine Learning

• Supervised vs. unsupervised learning
  • Key ML and DL algorithms (linear regression, decision trees, random forests)
  • Why Reinforcement Learning (RL)?

Module 10: Production Forecasting

• Time series analysis for production data
  • Building ML models for production forecasting

Module 11: Model Evaluation and Hyperparameter Tuning

• Metrics for AI model evaluation: RMSE, accuracy, F1-score
  • Model Explanation – Shapley Values

Module 12: Hands-On Exercise & Case Study

• Training and evaluating a production forecasting model
  • Optimizing production in a conventional reservoir using ML

Day 4: Advanced AI Techniques for Reservoir Engineering Module 13: Introduction to Deep Learning Models

• Neural networks and their applications in reservoir engineering
  • Introduction to TensorFlow and Keras

Module 14: Anomaly Detection in Reservoir Data

• Identifying equipment failures and production anomalies
  • Using autoencoders for anomaly detection

Module 15: Hands-On Exercise & Case Study

• Implementing anomaly detection on sensor data
  • Detecting and diagnosing anomalies in time series datasets

Day 5: Integrating Data Science into Business Decisions Module 16: Data-Driven Decision-Making

• Translating ML insights into actionable business strategies
  • Communicating results to stakeholders

Module 17: Challenges and Best Practices

• Data quality and availability
  • Model interpretability and explainability (Shapley Values revisited)

Module 18: Group Project

• Participants work in teams to solve a real-world reservoir engineering problem (ML & AI)

Module 19: Project Presentations and Course Wrap-Up

• Teams present their solutions
  • Discussion on future trends in data science and AI for reservoir engineering
  • Q&A and feedback

Key Takeaways

• Hands-on experience with Python and ML libraries
  • Ability to apply data science techniques to reservoir engineering problems
  • Understanding of how to integrate data-driven insights into business decisions
  • Certificate of completion

Materials Provided

• Course slides and lecture notes
  • Jupyter Notebooks with code examples
  • Datasets for hands-on exercises
  • Reading list for further learning