Open Tools for Machine Learning in Oil & Gas

Main instructor: Anna Dubovik (Gazprom-Neft, Russia)

Other instructors: Dmitry Podvyaznikov, Anton Broilovskiy, Antonina Arefina, Sergey Tsimfer, Svetlana Sorokina, Alexander Kuvaev, Alexander Koryagin, Alexey Kozhevin

Level: Intermediate (prior knowledge required)

Duration: 2 hours

Format this self-paced course consists of 8 introduction videos, pre-requisites and mandatory reading, combined with 8 quizzes

Registration opens soon


A certificate of attendance will be available upon completion of the course. After the end of the course, your certificate will remain available for download in your Profile page. For enrolling into an Advanced Machine Learning Course the certificate is required.

Brief course description

This course will introduce you to Open Machine Learning Tools that are tailored specifically to speed up data science in Oil&Gas sector. Please, be advised that this course mostly focuses on an audience that has prior experience with Machine Learning, does not cover the basics and focuses on applications. We kindly ask you to check course prerequisites before signing up.

During the course you will:

  1. Explore open libraries for building ML models

  2. Discover disadvantages of traditional approaches

  3. Learn how to build great quality control for ML solutions

  4. Understand the capabilities and limitations of deep learning algorithms

  5. Find out what manual tasks can already be converted to ML in Oil&Gas 

  6. Apply new knowledge in public industrial hackathons

Course prerequisites: mandatory to finish the course successfully 

  1. Basic machine learning understanding

We recommend to check Stanford ML lectures (not all, but few) 
View on YouTube (Lectures 1-4, 8-9, 11-13). This will put necessary terminology in order. 

  1. Beginner level of Python programming

We recommend to check simple 1 hour course (just enough)