Machine Learning Guide for Oil and Gas Using Python (DAT 607)
Machine Learning Guide for Oil and Gas Using Python (DAT 607)
COURSE SCHEDULE
| Code | Date | Location | price (€)* |
|---|---|---|---|
| DAT 607 | 19 - 23 Oct 2026 | Online | 3300 |
| DAT 607 | 24- 28 Aug 2026 | Stavanger | 4400 |
COURSE OVERVIEW
Machine Learning (ML) is a branch of Artificial Intelligence (AI) that enables engineers to make predictions and identify patterns without explicitly relying on physical models or governing equations. Instead, ML algorithms learn from historical data—such as production history—to forecast outcomes such as future oil production or reservoir performance.
This five-day course is designed to introduce and apply machine learning concepts across various areas of petroleum engineering. Participants will learn essential ML techniques and tools required to build, train, test, and deploy models from scratch.
The course uses Python—an open-source and user-friendly programming language—to develop practical workflows through widely used libraries and pre-built code modules. The training is conducted in an interactive environment, ensuring that the coding experience is straightforward, structured, and accessible.
No prior experience in machine learning, data science, linear algebra, or programming is required. The course is designed to guide participants step by step through the entire process. Anyone with an interest in applying AI and ML to extract valuable insights from petroleum data is encouraged to attend. At the same time, the course also accommodates participants with more advanced experience who wish to strengthen and expand their practical ML skills in petroleum applications.
COURSE OUTLINE
5 days
Day 1
o Machine Learning and Python applications
o Python installation (Anaconda installation)
o Jupyter Notebook interface and functionalities
o NumPy
Day 2
o Pandas data frame processing with completions data set examples
o Data visualization with Matplotlib and Seaborn
Day 3
o Data preprocessing
o Model Building for real-time drilling and production applications
o Unsupervised machine learning
Day 4
o Introduction to predictive model characteristics
o Linear Regressions for production optimization
o Logistic Regression for geologic facies classification
o K-Nearest Neighbor (KNN) for geologic log imputation
o Decision Trees (DT) and Random Forest (RF) for completions design optimization
o Support Vector Machine (SVM)
Day 5
o Neural Networks for sonic log generation and CUM/ ft production forecasting
o Model Evaluation for drilling, completions, reservoir, etc.
INSTRUCTOR
Dr. Hoss Belyadi
Hoss Belyadi is the Founder and CEO of Obsertelligence, LLC, a company specializing in artificial intelligence (AI) training and in-house technical solutions for the energy industry. He has served as an Adjunct Faculty member at several universities, including West Virginia University, Marietta College, and Saint Francis University, where he taught courses in data analytics, natural gas engineering, enhanced oil recovery, and hydraulic fracture stimulation design. With over 12 years of experience, he has worked on conventional and unconventional reservoirs worldwide and has led multiple machine learning projects. He has also delivered short courses for universities, professional organizations, and the U.S. Department of Energy (DOE). He is the primary author of Hydraulic Fracturing in Unconventional Reservoirs (1st and 2nd editions) and the author of Machine Learning Guide for Oil and Gas Using Python. He holds B.S. and M.S. degrees in Petroleum and Natural Gas Engineering from West Virginia University.
FAQ
DESIGNED FOR
o Engineers, software developers, data scientists, data engineers, data enthusiasts, business analysts, financial analysts, technical support, university professors, and even executives that would like to learn about this fascinating field
o Anyone in the organization who has the slightest passion for implementing AI, ML
o Advanced Python and ML users
COURSE LEVEL
o Intermediate to Advanced
LEARNING OBJECTIVES
Participants will learn:
o Learn basics fundamentals of Python programming.
o Deploy Oil and Gas related machine learning models.
o Learn fundamentals of the most used ML algorithms in the O&G industry.
o Heavy focus on optimization.
o Step by step code illustration using Python.
REGISTER
Registration is now OPEN!
Ph.D. students, group and early bird registrants are eligible to DISCOUNT!
For more details and registration please send email to: register@petro-teach.com
REQUEST IN HOUSE
Would you like a PetroTeach training course delivered at a time or location to suit you?
click for request in house