CodeDateVenueEarly Bird FeeFee
PE142316 - 20 Nov 2020Virtual Instructor Led Training (VILT) 5099 5299 Remind me of Course Dates
PE142316 - 20 Nov 2020Virtual Instructor Led Training (VILT) 15297 15897 Remind me of Course Dates

Code

PE1423

Date

16 - 20 Nov 2020

Venue

Virtual Instructor Led Training (VILT)

Early Bird Fee

5,099

Fee

5,299

Code

PE1423

Date

16 - 20 Nov 2020

Venue

Virtual Instructor Led Training (VILT)

Early Bird Fee

15,297

Fee

15,897

About this Virtual Instructor Led Training (VILT) 

This Virtual Instructor Led Training (VILT) aims to provide upstream professionals with a comprehensive introduction to the main machine learning methods and equip them with the hands-on experience in data science and machine learning. Through the VILT, participants will develop a solid understanding of supervised and unsupervised learning algorithms including advanced topics such as deep learning and machine learning models explainability.

The VILT has been designed to build up the participants’ confidence from scratch: starting with the introduction of each method in simple terms and followed by the detailed guidelines on how to apply different machine learning methods for solving actual problems from reservoir engineering, geomodelling, and petrophysics. The obtained knowledge from the VILT – combined with carefully designed code examples – can be used by participants in their ongoing and future projects that will aid in increasing their overall performance.

Note:

  1. All participants will need to use their own personal laptops (preferably with Windows OS, but Mac and Linux are also fine) as course materials and necessary software will be distributed by the trainer at the beginning of the VILT.
  2. It is recommended for participants to have 2 screens to optimise their learning.
  3. Good and stable internet connection for video conferences.

By the end of this VILT, participants will be able to:

  • Understand the core concepts of machine learning and data science.
  • Identify existing bottlenecks for machine learning methods application in your professional domain.
  • Choose the most appropriate machine learning methods to solve a particular problem.
  • Confidently apply the main machine learning methods in practice.

This VILT has been designed for Reservoir Engineers, Geologists and Petrophysicists who are willing to obtain a fundamental understanding and practical knowledge on scientific programming, data science and machine learning.

Prerequisite:

  • Participants should have upstream domain knowledge. Prior programming experience is a plus but not required.
  • The main machine learning methods will be discussed and illustrated with multiple reusable code examples and real data sets.
  • Solutions of multiple problems related to reservoir engineering, geology and petrophysics will be demonstrated using state-of-art machine learning libraries.

Your expert course leader has 14 years of experience in the Oil & Gas business and Data Science/Predictive Analytics. His background lies in applying machine learning methods for solving a large number of problems in reservoir engineering, reservoir simulation, geo-modelling and petrophysics.

He has a solid background in applying machine learning methods for solving a large number of problems in reservoir engineering, reservoir simulation, geo-modelling and petrophysics. He has extensive hands-on experience in building end-to-end data science solutions in the Upstream, E-commerce and Finance industry including statistical modeling of both regression and classification problems, supervised and unsupervised learning, data engineering, numerical optimisation and complex data visualization from requirement gathering, proof of concept design to production-level implementation.

His Oil and Gas experience includes an extensive track record of successful projects with NOC including Belorusneft, integrated field and reservoir study provider SGS Horizon as well as various clients across the globe such as majors, small/mid-size operators, banks and governmental institutions from the exploration kickoff phase to field development monitoring and very mature field revitalization program design. He has a solid background in both classic and simulation reservoir engineering including special topics (waterflood optimisation, compositionally-sensitive reservoir modeling).