Course description

Combining a design thinking approach with agile development, the course brings each participant from ideation to prototyping and try to address some defined issues in the Oil and Gas industry. 

As an introduction, we will look outside our industry and try to redefine innovation and try to answer some of the following questions: Why innovations matters? How can we boost it? Why people matter in a digital transformation? During this introduction, a human approach is adopted focusing on how we can adapt as an individual in the Age of Machine Learning and Artificial Intelligence by boosting our own creativity. 

The course then focuses on Design Thinking and Agile development and these techniques help navigate within this new paradigm. We try to answer some of the underlying questions through a structured framework allowing the participant to move from Inspiration to Ideation, and, from Ideation to Implementation. 

This then is followed by a more focused look on the Implementation stage and the use of Machine Learning and Artificial Intelligence tools to solve G&G problematics. During this stage, we investigate what are the pitfalls and lessons learnt from the management of Machine Learning projects covering architecture and data issues.

Finally, the course shifts into a hackathon mode, allowing the participants to develop and implement their prototype and to test their ideas with end-users and test it within their organization.

Course objectives

Upon completion of the course, participants shall be able to:

• Define what is innovation and why it matters

• Boost their innovation through creativity

• Apply a Design Thinking framework to a specific problem

• Code a Machine Learning prototype using agile development

• Monitor, manage and engineer new Machine Learning project 

The course is not:

• A python development course for developers

• A pure Machine Learning course defining the different types of algorithms available

Course outline

The course intends to be conducted in a team format with 3-4 members per team, highly collaborative combining soft knowledge (creativity, innovation) with hard knowledge (statistics, mathematics).

The course is split into 2 with:

• A first part (2 days) which is conducted in the format of a formal course with the instructor, with lectures, hands-on exercise, programming short crash courses and design thinking exercises.

• A second part (2 days) which is following the traditional hackathon setup, working autonomously in teams.

It is recommended that both parts are attended by the participants, providing participants with the full experience. However, opportunities are given to the participants to only register to the first part – related to the course part with instructor.

First Part - Course:

The course is modular and split into the following:

1. Lectures:

1. Innovation: Why it matters? And how to boost it? (0.5 day)

2. Design thinking: Inspiration, Ideation, Implementation (0.5 day)

3. Toolbox for a successful ML/AI perspective implementation (0.5 day)

2. Programming crash courses (20 min. each)

3. Hands-on team exercises

By the end of the course session, the participants should have been able to 1. Identify the problem they want to solve 2. Build a non-working/non-programming mock-up of their prototype that they will be able to test during the hackathon stage.

Second Part - Hackathon:

The hackathon will put into motion the mock-up proposed at the end of the lecture sessions and work within teams to develop and test a Minimum Viable Product (MVP). 

At the end of the hackathon, each team presents a Minimum Viable Product (MVP) to the jury.

Participants' profile

The course is designed for geoscientists (geology/geophysics), petroleum engineers, petrophysicists and data scientists from new ventures/basin, exploration, and development & production disciplines - from recently graduated to seniors, working in oil & gas companies or service companies. No prerequisites required.

Francois Baillard, Iraya Energies

Iraya Energies is a scale-up company specialized in Machine Learning applied to Geoscience and Engineering, focused in the field of managing unstructured data within the Oil and Gas industry. In Iraya, he is responsible of the R&D, implementing new Machine Learning/Artificial Intelligence technologies covering supervised and unsupervised learning for Deep Technologies to extract valuable knowledge from unstructured data.