3 SHORT COURSES
13 April 2025
Participants can choose to attend 1 full day course from 3 exciting short courses on offer.
Workshop Course: Reservoir Simulation Fundamentals
(Reviewed by the technical committee)
Instructed by Dr. Leonardo Patacchini (Stone Ridge Technology)
About the instructor
Leonardo Patacchini, joined as the Regional Director (Europe and Middle East) of SRT in February 2019 after a decade with TOTAL as a Reservoir Engineer based in France, the United Arab Emirates and Scotland. Leonardo has an Engineering degree in Physics from Ecole Polytechnique (France) and a PhD in Applied Plasma Physics from MIT.
Overview
The aim of this course is to review a wide selection of reservoir simulation concepts needed to build and run a dynamic model. Topics of discussion include introduction to reservoir simulation and the underlying mathematics, grids, aquifers, PVT data, rock and fluid data, initial conditions, time dependent data, and troubleshooting. Given the one-day course format, the material will be covered at an overview level with opportunities to delve deeper into topics when questions are asked.
Participants’ profile
The course is highly beneficial for early to middle career subsurface professionals: reservoir geologists, reservoir engineers, petroleum engineers, petrophysicists and managers.
Participants’ profile
The course is highly beneficial for early to middle career subsurface professionals: reservoir geologists, reservoir engineers, petroleum engineers, petrophysicists and managers.
Course Outline:
Session 1: Numerics and gridding 9:00 am – 10:30 am
- Introduction to reservoir simulation
- Numerical schemes and solvers
- Reservoir simulation grids
Session 2: Physical models 11:00 am – 12:30 pm
- PVT
- Rock-fluid
- Initialization of simulation studies
Session 3: Advancing the simulator through time 1:30 pm – 3:00 pm
- Well models and controls
- Discrete events handling
- Coupling to surface facility models
- Numerical tunings and performance
Workshop Course: Introduction to Machine learning applied for reservoir characterization
(Reviewed by the technical committee)
Instructed by Dr. Ahmad Abushaikha (Hamad Bin Khalifa University)
About the instructor
Dr. Ahmad Sami Abushaikha is a founding faculty member. He received his BS in Petroleum Engineering and his BA in Economics from the University of Texas at Austin in 2004. In 2006, he received his MS in Reservoir Geosciences and Engineering from "Institut Français du Pétrole". From 2007 to 2009, he worked at TOTAL Research Centre at Pau, France and at Qatar Petroleum. In 2013, he received his PhD in Petroleum Engineering from Imperial College London. From 2015 to 2017, he was a Postdoctoral Research Fellow at Stanford University specializing in discretization schemes for fluid flow in porous media.
Overview
“Introduction to Machine Learning Applied for Reservoir Characterization" is a course designed to provide attendees with a foundational understanding of machine learning techniques and their applications in the oil and gas industry, specifically for reservoir characterization. The course covers key machine learning concepts, including supervised and unsupervised learning, data pre-processing, and model validation, while focusing on their implementation in subsurface modeling. Attendees will explore how machine learning can be used to predict reservoir properties, enhance data interpretation, and optimize field development strategies, with practical examples and case studies relevant to the energy sector.
Participants’ profile
This course is designed for professionals, researchers, and graduate students in the energy industry who are interested in applying machine learning and reinforcement learning techniques to reservoir characterization.Course Outline:
Session 1: Fundamentals of Machine Learning and Applications in Reservoirs 9:00 am – 10:30 am
- Overview of Machine Learning in Oil & Gas: Key Concepts and Techniques
- Supervised vs. Unsupervised Learning: Understanding Reservoir CharacterizationApplications
- Machine Learning Algorithms Overview: Regression, Classification, and Clustering forReservoir Properties
Session 2: Data Pre-Processing and Feature Engineering 11:00 am – 12:30 pm
- Data Pre-Processing: Handling Missing Data, Noise, and Outliers in Reservoir Data
- Feature Engineering: Extracting Meaningful Features from Geological and Petrophysical Data
- Data Preparation Workflow: Steps from Raw Data to ML-Ready Dataset
Session 3: Model Development, Evaluation, and Case Studies 1:30 pm – 3:00 pm
- Building and Validating Predictive Models for Reservoir Characterization
- Evaluation Metrics and Model Optimization Techniques
- Case Studies and Practical Examples: Applications of ML in Predicting Reservoir Properties
Course Outcomes:
Attendees will understand core machine learning principles and workflows tailored to reservoir characterization. They will gain insights into data preparation, model selection, and practical applications, supporting enhanced decision-making for subsurface modeling.
EAGE Course: Upscaling and Artificial Intelligence Based Proxies for Uncertainty Assessment of Reservoir Production
(Reviewed by the EC and included in the official EAGE course portfolio)Instructed by Prof. Dr. Dominique Guérillot (Terra 3E)
About the instructor
Dr. Dominique Guérillot has been appointed as a professor in the Petroleum Engineering Program at Texas A&M University. He previously served on the executive committee of the Institut Français du Pétrole (2001–2006) and was head of reservoir research at Qatar Petroleum (2013–2015). Currently, he is the President and CEO of Terra 3E SAS, an innovative company. Dr. Guérillot has authored over 50 peer-reviewed papers and holds five patents. He earned his Ph.D. in applied mathematics from Aix-Provence Université, France.
Overview
The aim of the course is to recap main techniques required to build an integrated reservoir model and to explain different potential workflows for field development and/or history matching processes. This course will include explanations of upscaling techniques and the use of proxies for uncertainty assessment of production forecasts. You can find more information about this course through the EAGE short course catalogue link here.
Participants’ profile
The course is primarily addressed to reservoir geologists and reservoir engineers involved in building reservoir models but could also be of interest to production engineers who have to deal with the consequences of uncertainty in reservoir performance.Course Outline:
Session 1: Reservoir Characterization & Simulation 9:00 am – 10:30 am
- Integrated Geological Modeling and Reservoir Simulation
- Geostatistics
- Variogram
Session 2: Kriging and Geostatistical Simulations 11:00 am – 12:30 pm
- Kriging
- Geostatistical Simulations
Session 3: Upscaling and Uncertainty in Production Forecast 1:30 pm – 3:00 pm
- Upscaling
- Uncertainty Assessment in Production Forecast
- Applications
Course Outcomes:
Participants will learn to integrate geological and reservoir simulation models, effectively upscale geological data for reservoir simulators, and explore methodologies for assessing uncertainties in production forecasts using AI-based proxies of reservoir simulators.
