| Code | Date | Format | Currency | Team of 10 Per Person* |
Team of 7 Per Person* |
Early Bird Fee Per Person |
Normal Fee Per Person |
|---|---|---|---|---|---|---|---|
| PE2236 | 29 Jun - 03 Jul 2026 | Kuala Lumpur, Malaysia | SGD | 5,503 | 5,759 | 6,199 | 6,399 |
| PE2236 | 29 Jun - 03 Jul 2026 | Kuala Lumpur, Malaysia | USD | 4,299 | 4,499 | 4,799 | 4,999 |
*Fee per person in a team of 7 or 10 participating from the same organisation, registering 6 weeks before the course dateRequest for a quote if you have different team sizes, content customisation, alternative dates or course timing requirements Request for in-person classroom training or online (VILT) training format
Learn in teams and save more! Enjoy group discounts of up to 50% off normal fees for team based learning. Contact us on [email protected] to learn more today!
Code
PE2236Date
29 Jun - 03 Jul 2026Format
Kuala Lumpur, MalaysiaCurrency
SGDTeam of 10
Per Person*
5,503
Team of 7
Per Person*
5,759
Early Bird Fee
Per Person
6,199
Normal Fee
Per Person
6,399
Code
PE2236Date
29 Jun - 03 Jul 2026Format
Kuala Lumpur, MalaysiaCurrency
USDTeam of 10
Per Person*
4,299
Team of 7
Per Person*
4,499
Early Bird Fee
Per Person
4,799
Normal Fee
Per Person
4,999
*Fee per person in a team of 7 or 10 participating from the same organisation, registering 6 weeks before the course dateRequest for a quote if you have different team sizes, content customisation, alternative dates or course timing requirements Request for in-person classroom training or online (VILT) training format
About this Training
This 5-day training course provides upstream oil and gas professionals with a structured, hands-on introduction to data science and machine learning, specifically tailored to subsurface and production workflows. Participants build a strong foundation in scientific programming, data wrangling, visualization, and statistical thinking before progressing to modern machine learning techniques used across reservoir engineering, geoscience, and production analytics.
The program bridges domain expertise and advanced analytics by demonstrating how supervised and unsupervised machine learning methods can be applied to real upstream challenges such as production forecasting, electrofacies and lithofacies identification, decline curve analysis, volumetrics uncertainty, anomaly detection, and waterflood optimization. Each method is introduced conceptually and then reinforced through practical exercises using realistic field and well data.
By the end of the course, participants gain the ability to design end-to-end analytical workflows, from raw data ingestion to model interpretation, using open-source Python libraries widely adopted in industry. Emphasis is placed on model explainability, uncertainty awareness, and reproducibility, ensuring that machine learning results can be confidently communicated to both technical teams and decision-makers.
Upon completion of this course, participants will be able to:
- Apply machine learning methods confidently to upstream engineering and geoscience problems, aligning algorithms with data quality, business objectives, and reservoir complexity.
- Build reproducible, end-to-end data science workflows using Python for production data analysis, reservoir studies, and subsurface modelling.
- Evaluate uncertainty and optimize decisions using probabilistic methods, numerical optimization, and data-driven forecasting.
- Implement and interpret advanced machine learning models, including clustering, regression, classification, and neural networks, with a focus on explainability.
- Translate analytical results into actionable insights, supporting reservoir management, development planning, and operational optimization.
This course is designed for experienced upstream professionals who want to systematically integrate data science and machine learning into their technical workflows rather than treat AI as a “black box.”
- Reservoir Engineer
- Production Engineer
- Petroleum Engineer
- Geologist / Reservoir Geoscientist
- Petrophysicist
- Subsurface or Integrated Asset Engineer
- Upstream Data Analyst or Technical Specialist
- Digital Transformation or AI Champion (Upstream)
- Basic
- Intermediate
The course follows a hands-on, problem-driven learning approach combining concise theory sessions with extensive practical exercises. Participants work with real-world upstream datasets using guided Python notebooks, enabling immediate application of concepts such as data preparation, model training, validation, and interpretation. Interactive discussions, step-by-step workflows, and domain-specific case studies ensure practical relevance and knowledge retention.
Your expert course leader is a petroleum engineer and data science leader with over 20 years of international experience spanning upstream oil & gas, advanced analytics and management consulting. He has held senior technical and leadership roles at Belorusneft (NOC), SGS Horizon and McKinsey & Company, where he led and delivered end-to-end machine learning solutions addressing complex engineering and business challenges. He currently specializes in helping upstream professionals operationalize data science and machine learning through practical, explainable, and value-driven workflows grounded in real subsurface and production applications.
Unlock the potential of your workforce with customized in-house training programs designed specifically for the energy sector. Our tailored, in-house courses not only enhance employee skills and engagement but also offer significant cost savings by eliminating travel expenses. Invest in your team’s success and achieve specific outcomes aligned with your organization’s goals through our expert training solutions. Request for further information regarding our on-site or in-house training opportunities.
In our ongoing commitment to sustainability and environmental responsibility, we will no longer providing hard copy training materials. Instead, all training content and resources will be delivered in digital format. Inspired by the oil and energy industry’s best practices, we are leveraging on digital technologies to reduce waste, lower our carbon emissions, ensuring our training content is always up-to-date and accessible. Click here to learn more.
To further optimise your learning experience from our courses, we also offer individualized “One to One” coaching support for 2 hours post training. We can help improve your competence in your chosen area of interest, based on your learning needs and available hours. This is a great opportunity to improve your capability and confidence in a particular area of expertise. It will be delivered over a secure video conference call by one of our senior trainers. They will work with you to create a tailor-made coaching program that will help you achieve your goals faster.
Request for further information post training support and fees applicable
Q1: What is machine learning in upstream oil and gas applications?
Machine learning in upstream oil and gas refers to the use of data-driven algorithms to identify patterns, predict outcomes, and support decisions in exploration, reservoir engineering, and production. Typical applications include production forecasting, facies classification, anomaly detection in wells, decline curve analysis, and uncertainty quantification. These methods complement physics-based models by extracting insights from large and complex datasets.
Q2: How does machine learning differ from traditional reservoir engineering methods?
Traditional reservoir engineering relies heavily on physics-based models and deterministic assumptions, while machine learning focuses on learning relationships directly from data. Machine learning can rapidly analyze large datasets, handle nonlinear relationships, and support screening and optimization tasks. However, it does not replace physics-based models; instead, it enhances them by improving speed, scalability, and uncertainty awareness.
Q3: What types of data are commonly used in upstream machine learning?
Common data sources include production and injection data, well logs, pressure and PVT data, reservoir simulation outputs, static model properties, and operational time-series. Data quality, consistency, and representativeness are critical, as machine learning models are highly sensitive to noisy, biased, or incomplete datasets.
Q4: What are the main challenges of applying machine learning in upstream projects?
Key challenges include limited data volume, inconsistent data quality, strong geological heterogeneity, and the need for model interpretability. Organizational challenges such as lack of integration between domain experts and data scientists also play a major role. Successful applications require close alignment between engineering knowledge and analytical methods.
Q5: How is uncertainty handled in machine learning for reservoir studies?
Uncertainty is addressed through probabilistic methods, ensemble modeling, cross-validation, and scenario analysis. Machine learning can be combined with Monte Carlo simulations and statistical techniques to quantify the impact of uncertain inputs on predictions, supporting risk-aware decision-making rather than single deterministic forecasts.
Q6: What is model interpretability and why is it important?
Model interpretability refers to understanding how input variables influence machine learning predictions. In upstream engineering, interpretability is essential for trust, QA/QC, and regulatory or management acceptance. Techniques such as feature importance, partial dependence, and explainable AI methods help engineers validate results against physical intuition.
Q7: Can machine learning replace reservoir simulation?
Machine learning cannot fully replace reservoir simulation, as it does not explicitly model physical processes. However, it can act as a powerful surrogate for screening, optimization, uncertainty evaluation, and rapid forecasting, significantly reducing computational cost and supporting faster decision cycles.
Q8: What is the future outlook for machine learning in upstream oil and gas?
The future lies in hybrid workflows that combine physics-based models, data-driven methods, and automation. Advances in explainable AI, digital twins, and real-time analytics are expected to increase adoption, enabling more adaptive reservoir management and integrated asset optimization.
Learn what past participants have said about EnergyEdge training courses
What I liked most about the course was the quantity of exercises and relating them to real-life cases. The notebooks are very clear and well organised.
Exploration Systems Analyst at Saudi Aramco
The practical scripts can be used in my job immediately.
Geophysicist at PTTEP
Excellent content of the course, newly introduced concepts for me and information which also was combined with the examples that made it easier to understand.
Sr. Petroleum Engineer at Saudi Aramco
I liked the examples and the way the instructor explained the logic behind without going deeply into the codes.
Reservoir Engineer at Wintershall Dea
I liked the practical aspect of the course, the use of notebook and ability to use the same codes in the future. The instructor was really well qualified and great delivery.
Reservoir Engineer at CNOOC
I really enjoyed the course and the trainer perfectly delivered the course with full experience and knowledge. The content is amazing and exceeded the expectations.
Petroleum Engineer at Saudi Aramco
Related Courses
