About this Virtual Instructor Led Training (VILT)
The 4th Industrial Revolution (IR4) Technologies are transforming the way we work and accomplish daily tasks in the Oil & Gas industry, by increasing efficiency and reducing redundancy. At the forefront of these technologies is Artificial Intelligence (AI), a field of study that instructs machines to mimic human actions, which has had significant growth in the past two decades, by the increased use of digital data.
This Virtual Instructor Led Training (VILT) goes through the fundamentals of machine learning, ties it to applications in the Oil & Gas subsurface sector and exposes the participants to real-life case studies that can significantly impact the way we work in the future.
- Learn and apply python programming for data science and analytics problems
- Be able to identify the right tools and techniques to approach either a regression or classification problem in a subsurface predictive analytics project
- Understand time series algorithms that form sensor data and interdependency between instances
- Distinguish different machine learning algorithms like anomaly detection, trees, and linear models to apply in any machine learning problems in subsurface
- Deploy a machine learning project to either cloud or on-premise server
This VILT is specifically designed for subsurface engineers and geoscientists, technical authorities and related professionals interested to learn the concepts and applications of data science and machine learning in the subsurface sector of the Oil & Gas industry.
This VILT will be delivered online in 5 half-day sessions comprising 4 hours per day, with 2 breaks of 10 minutes per day. Q&A sessions will be taken via the online platform either during the class or after each module. Activities and tutorials will follow physical class pattern, i.e. after each module, the participants will have time to complete tutorials either individually or in a group, depending on the activity type.
Your expert course leader’s experience begins from being a Manufacturing Research Engineer at Schlumberger REMS, adjunct professor at IPE Heriot Watt University to a Senior Data Scientist at Shell. He has built and delivered various analytics solutions in identifying root causes via clustering algorithms, digitalising data collection and monitoring system, forecasting system failures before major mishaps, identifying lithofacies and many other natural language processing solutions to summarise text data and perform sentiment analysis to name a few. Recently, he was also a part of Shell’s digital coaches to transform the workforce into being digital and agile savvy, especially in the area of data and analytics. He holds a Master of Science Degree in Petroleum Engineering from the Institute of Petroleum Engineering, Heriot-Watt University, Edinburgh. He also qualified with a Bachelor of Engineering in Electrical and Electronics Engineering (Honours) majoring in Artificial Intelligence and Robotics.
He is an expert and trains in a broad range of technical development including:
- Python Programming, Data Science and AI
- Machine Learning and Artificial Intelligence
- Petroleum Economics
- Petroleum Reservoir Rock Evaluation
- Basics and Advanced Calculus and Statistics
- Application of Data Science and Analytics in Oil and Gas Production, Operations and Maintenance