New Applications of Machine Learning to Oil & Gas Exploration and Production

Course Description

The course introduction will attempt to answer the question: How will A.I. change the way we work in the Oil and Gas industry in the coming years? Looking at what is underway in other industries and guessing what type of projects are under development in R&D departments in our industry will help answer that question.

Oil and Gas examples will be presented corresponding to each of the terms A.I., Machine Learning, and Deep Learning, allowing participants to reach a clear understanding on how they differ.

The course will then focus on Deep Learning (DL) and address all key aspects of developing and applying the technology to Oil and Gas projects.

• What is DL and how different is it from traditional neural networks?
• A peek at the mathematics behind Deep Neural Networks (DNN)
• Typical workflow to design and develop a deep learning application in an E&P project
• Common challenges, difficulties, and pitfalls in deep learning projects
• Software tools and hardware required + Cloud computing vs in- house solutions.

This will be followed by live demonstrations of two DNN-based applications specific to Oil and Gas upstream domains.

First, we’ll run software performing automatic fault identification on released seismic data from New Zealand basins to demonstrate how a DNN recognizes faults and how it differs from other algorithms such as ant tracking. Starting from default training, the DNN can gradually learn to recognize faults like the Geophysicist or Structural Geologist. The training set constantly evolves incorporating feedback from human experts.

Second, the identification of resource opportunities in very large repositories of text and image documents will be demonstrated. This will be done with a deep learning application that performs contextual search and linguistic analysis. Unlike keyword search, contextual search extracts information based on its context, just like humans do. And then linguistic analysis is run on the extracted information to identify actionable opportunities. This list of opportunities can then be further evaluated by human experts.

Finally, the course conclusion will summarize key learnings and answer any additional questions/queries from participants.

Course Objectives

Upon completion of the course, participants will have acquired detailed knowledge of what deep learning is exactly, how it works, and in which way it differs from traditional neural networks that have been used in the industry during the last 30 years. They will understand which domains this can be applied to and for what type of applications. And they will also understand what are the main challenges, difficulties, and pitfalls when developing new applications. Finally, they will have seen demonstrations of deep neural networks applied to Exploration and Production disciplines and will be able to evaluate how useful the technology could be for their own domain.

Course Outline

Morning session: 3 hours + breaks. Lunch break. Afternoon session: 3 hours + breaks

• Introduction to the new A.I. world: What’s currently underway in R&D departments?
• Artificial Intelligence, Machine Learning, and Deep Learning: how do they differ and examples of O&G applications
• A closer look at Deep Learning:
• What is it and how different is it from traditional neural networks?
• A peek at the mathematics behind Deep Neural Networks (DNN) 
• Typical workflow to design and develop a deep learning application in an E&P project
• Common challenges, difficulties, and pitfalls in deep learning projects
• Software tools and hardware required + Cloud computing vs in- house solutions.
• Application to Geophysics and Geology: automatic fault identification with a DNN (live)
• Application to Production Engineering: detecting oil & gas opportunities with a DNN (live)
• Conclusion - Key learnings

Participants’ Profile

The course is designed for geoscientists, petroleum engineers, and petrophysicists from new ventures/basin, exploration, and development & production disciplines - from early career to senior, working in oil & gas companies or service companies.

About the Instructor

Dr. Bernard Montaron is CEO of Fraimwork SAS, Paris, France, and CTO of Cenozai Sdn Bhd, Kuala Lumpur, Malaysia. Two startups created in 2017 that are specialized in the application of AI to various domains, and provide services to oil and gas companies for exploration and production. In 2015-2017 he was Chief Geoscientist of Beicip Tecsol in Kuala Lumpur. Prior to this, Bernard Montaron worked 30 years for Schlumberger where he held a number of positions in R&D and Marketing. He has worked for the oil and gas industry in Europe, in the US, in the Middle East, in China, and Malaysia. Bernard was General Manager of the Schlumberger Riboud Product Center in Paris – Clamart, France (2002-2003) and he was VP Marketing of Schlumberger Middle East and Europe-Africa-Russia regions (2000-2001). Bernard holds a MSc degree in physics from ESPCI, Paris, and a PhD in Mathematics from University Pierre et Marie Curie, Paris. He has a Machine Learning certificate from Andrew Ng’s course (Stanford Univ./Coursera). Bernard received the best oral presentation award at the APGCE 2017 conference for his paper on “Deep Learning Technology for Pattern Recognition in Seismic Data – A Practical Approach”.