Webinar: Summary and results from the Force 2020 Machine Learning Contest

seismic wells

Peter Bormann from ConocoPhillips will be presenting the results from the FORCE 2020 Machine Learning contest. Dont miss out on this great event.

Date Time Duration Register by Location
11.02.21 11:00 45 min 11.02.21 Teams

 

 

 

Authors

Peter Bormann, Principal Geologist- ConocoPhillips
Peter.bormann@cop.com


Peder Aursand, Senior Engineer – Machine Learning- AkerBP
peder.aursand@akerbp.com

 

Abstract

The current revolution in data science / machine learning is fueled by open data sets, a democratization of tools and global real time access of knowledge and innovation. For this reason globally open competitions with subsurface data offer an intriguing way of testing the current state of the art in the field of machine learning.

In early 2020 five people from 5 different companies got together to organize the first truly open machine learning competition on well data and seismic under the auspices of FORCE; A cooperating forum of Norwegian Oil&Gas companies and the authorities.

Over 400 truly globally distributed teams and close to 2000 individuals participated in predicting lithology from well logs and identifying faults on seismic.

We will present the results of the competition, compare the machine learning outcomes against expert geological interpretations and disclose the winning teams’ algorithms.

The machine learning competition will well log data attracted most interest with over 300 teams submitting solutions to a tightly contested leaderboard. The top 10 algorithms are very close in terms of their ability to determine lithofacies from well logs alone and the machine predictions are on par or even surpass human interpretations. The fact that none of the algorithms achieved more than 80% correctness is likely a result of the ambiguity in interpretation of closely related lithofacies classes such as shale and silt or chalk and limestone. Still, further improvements to the algorithms, datasets and the way the competition was run are currently being researched by a global community of geodatascientists. The unique provided open dataset will serve as an industry benchmark for the coming years.

 

How a webinar works

You register as usual through the registration button above. Once you are registered you will get an invitation via email to join this webinar. 
FORCE uses Teams Video for this webinar, and has proven to work successfully. 

We recomment that everyone joining turn off their camera and microphone when joining.
If you have any questions you can use the chat or wait until the end of the talk.

 

FORCE seminars have previously been fully booked with waiting lists so you are encouraged to sign up as soon as you know you will attend.

Participation fees:

FORCE members: Free
Non-members: NOK 350,-
University/student: Free

 

Important information:
You can register as a FORCE member and pay "FORCE member" price if you are an employee of a member company.
All FORCE member companies are listed here.

Payment is made online by credit card. Please note that no refunds will be given after you have signed up.
If you for any reason can not attend the workshop, you are welcome to send a representative, just inform Linn Smerud as soon as there are changes. 

 

If you have any questions please contact Linn Smerud at the FORCE secretariat.

 

Updated: 11/02/2021