Course content

Traditional education in petroleum engineering does not provide sufficient exposure to digitalization and automation technologies. A strong foundation in these areas enables petroleum engineers and decision-makers to recognize opportunities for digital transformation within their domains, communicate effectively with technology developers and vendors, maximize the value of these innovations, assess their business impact, and identify and mitigate associated risks. This course aims to bridge this gap for engineers, researchers, and decision-makers by integrating digital and automation concepts into drilling operations.

The course covers the following topics, with a focus on applying digitalization, automation, and data-driven approaches in the oil and gas industry:

• Measurement and collection of drilling data, including real-time and raw data acquisition.
• Data transmission and downhole measurement techniques.
• Introduction to Python programming for drilling applications.
• Application of Python and the NumPy library for various drilling calculations.
• Utilizing the Pandas library for data handling in drilling processes, including well hydraulics, managed pressure drilling (MPD), casing load analysis (CML), drilling problem detection, well control, and trajectory design.
• Visualization and analysis of drilling data using Matplotlib.
• Automation of drilling sequences and analysis using Seaborn and Scikit-Learn libraries.
• Machine learning techniques relevant to drilling, such as linear regression, random forests, decision trees, and gradient boosting.
• Implementation of machine learning models for drilling and geoscience applications, including rate of penetration (ROP) optimization and formation prediction.

Learning outcome

Competence

After completing the course, the student will be able to:

• Identify opportunities for applying digital and automation technologies in upstream oil and gas operations.
• Evaluate the suitability, implementation, and business impact of Python-based and AI-driven solutions in drilling and geoscience workflows.
• Communicate effectively with technology developers and stakeholders to support digital transformation initiatives.
• Assess risks and propose mitigation strategies related to the deployment of automation and machine learning systems.

Knowledge and Skills

After completing the course, the student will be able to:

1. Understand the foundations, benefits, and limitations of digitalization and automation in petroleum engineering.
2. Apply Python programming and libraries (NumPy, Pandas, Matplotlib, Seaborn, Scikit-Learn) to analyze drilling and geoscience data.
3. Perform data acquisition and transmission tasks, including real-time and downhole measurements.
4. Use machine learning models (e.g., linear regression, decision trees, random forests, gradient boosting) for drilling optimization and formation prediction.
5. Analyze drilling hydraulics, casing design, well control, and trajectory design using data-driven approaches.
6. Automate drilling sequences and workflows using Python and ML tools.
7. Detect and interpret drilling problems using digital analytics and predictive modeling.
8. Evaluate the integration of digital tools in managed pressure drilling (MPD), controlled mud level (CML), and other advanced techniques.
9. Design and critically assess implementation plans for digital solutions in drilling operations.
10. Present and communicate technical findings and business evaluations of digital technologies in petroleum engineering.

Learning methods and activities

The course is part of NTNU's Continuing Education courses and has a course fee. See NTNU Continuing Education. The course will be given under the condition of sufficient number of participants. The course is session-based, with two sessions per semester, of 3 days each, with self-study, exercises, and a project between the sessions. The course will be given in English.

Recommended previous knowledge

Experience in upstream petroleum technology.

Required previous knowledge

Engineer/Bachelor's/Master's degree in a technical discipline.

Course materials

Lecture notes, selected papers and publications.

Digitalization: Python Application for Drilling & Geoscience Engineer

- ISBN: 978-620-6-18422-5