Data Analytics: Machine Learning: Usability, Stability & Interpretability

When:  Jun 25, 2019 from 11:30 AM to 01:00 PM (MT)
Associated with  Calgary Section

Data Analytics Luncheon:
Machine Learning: Usability, Stability &
Interpretability

Date: Tuesday, 25th of June 2019
Speaker: Bertrand Groulx, Verdazo Analytics
And
John Hirschmiller, GLJ
Location: Petroleum Club
Time: 11:30 AM - 1:00 PM 
Cost:
Members: $45, Non-Members: $55, Student: $15 


Abstract:

Machine learning in the Oil & Gas industry has met with varied success and no shortage of hype.  Barriers to success in the industry include data challenges, inflated expectations, and a lack of trust from those who stand to benefit from its results.  In this presentation, we will be showing the bulk of our Spirit River Study from the SPE Subsurface Workshop, plus a whole lot more.  We will explore trust-building approaches that include feature selection, interpretive visualizations, stability considerations, “What’s a good R2?”, and a Man vs Machine simulation.  In the simulation, we compare traditional type-curve generation approaches with those based on machine learning models, using data from the Marcellus.  You will leave wondering if your existing type curving methodology is the best you can do with the data you have available.  It promises to be fast-paced and engaging.

Speaker Bio:

Bertrand is co-founder and President of Verdazo Analytics and has championed the company’s oil and gas analytic pursuits for 14 years. He has a diverse educational background that includes physics, geology, and industrial design. Over a 20-year career in the upstream energy sector, Bertrand has worked in over 11 countries assisting more than 130 companies to develop workflows, analysis methodologies, and data visualization solutions. Leveraging the crowdsourcing of industry experts, he has compiled a library of best practices and shared his insights through a variety of social media, SPE and industry presentations. In recognition of his contributions to the industry, he was awarded the 2016 SPE Canada Production and Operations Award and nominated to be an SPE Distinguished Lecturer. He now leads Verdazo’s machine learning research and consulting practice

John Hirschmiller holds a B.Sc. (Hons) in Earth Sciences from Dalhousie University and is a Professional Geoscientist with GLJ Petroleum Consultants. John is responsible for geological interpretations for use in reserves and resources reporting, A&D support, regional resource play evaluations, and the quantification of geologic risk and uncertainty. John’s Canadian experience is largely in unconventional and tight reservoirs in resource plays, including the Spirit River, Duvernay, Montney, Ellerslie, Viking and the oil sands. Internationally, John has worked on projects on six continents, particularly in Latin America.

.

 
Don't miss out and sign up today!



Is your Membership up-to-date? Are you looking to become an SPE Member? Learn more here!

​​​​​​

Location

Calgary Petroleum Club
Devonian Room
Calgary, AB
Canada