BookmarkSubscribeRSS Feed

Predict the zone in a well path

Started ‎03-30-2021 by
Modified ‎10-20-2022 by
Views 2,199
Team Name Well Learners
Track Industry - Energy
Use Case Predict the zone in a well path
Technology SAS Viya, Python
Region EMEA
Team lead Nithya Mohan
Team members Looking for team members

 

Predict zone for a well based on different well logs acquired along the reservoir part of wells. Use different Model types and benchmark which ones perform better. Currently zone prediction is done manually and sequentially one well at the time as wells are drilled in an area. The manual interpretation is done by Petro physicists using logs signature and general area and geological knowledge in addition to his/her knowledge and experience with the physical principles behind the log measurements. There is a potential to produce more consistent and unbiased predictions by data-driven methods.

 

A zone is a subdivision of the rocks in the subsurface based on rock quality and fluid properties, i.e., how porous is the rock, is it fill with water, oil or gas or a mix? is the rock dense and tight or porous and fractured etc., this leads to different log responses when it comes to sound velocity, nuclear background radiation etc. Note that only have indirect log measurement of the variation of physical properties along a borehole filled with drilling mud of a specific composition. We have no direct measurement of porosity or rock types. The problem is to predict a discrete zone (target) log from N (N<10 typically) feature (petrophysical and continuous) logs. Zone log is also often called lithology log.

 

I have a dataset with 28 030 011 rows and 136 columns.. I need to mask the well name, zone name and XY coordinates and then it’ll be ready for the hackathon by next week

 

 

Comments

Hello Nithya,

 

My partner rep told me that you are looking for team members. I have experience using Python and Viya and would be happy to help with the project! Let me know if you are interested.

 

Michael Shealy

michael.shealyjr@cachedconsulting.com

@michael_shealy2 - I've sent an email to you to help connect you with @nithya-mohan as part of her team.

I am Keith Holdaway, a geophysicist who has worked at SAS for the past 24 years as a software developer and advanced analytics model builder in O&G; particularly in the upstream subsurface sectors.

 

I am the chief business developer for SAS Global O&G digitalization, currently working in the IoT arena.

 

Over the past 12 years, I have helped SAS O&G customers garner business value from data-driven analytical workflows.

 

I have visited CoP several times in Houston and twice in Stavanger.

 

I have just be asked by SAS to be a mentor and assist your team in the Hackathon.

 

I’m still learning the channels of communication and protocols established by SAS.

 

So, I thought it easiest to initially reach out and introduce myself.

Apparently I can order team T-shirts if you can send me your sizes.

 

Keith

Hi Keith that we great that you got in touch.. We have managed to upload data and going through the exploring phase now.. I can include you in the Meeting on Monday and we can have a discussion?

 

Nithya

@keholdgreat that you got in touch.. We have managed to upload data and going through the exploring phase now.. I can include you in the Meeting on Monday and we can have a discussion?

 

Nithya

Please include me if you need any help.

 

Keith

Can I download data?

way cool, 🆒 good luck !

Nithya-Mohan,

Did you have a meeting today to discuss the data?

Please let me know if you need help analyzing.

Can you share with me at least the data model?

Any other collateral?

Keith

 

Nithya

I just watched your 12 minute video covering your work.

I think you made some solid progress.

Interesting that you mentioned identifying Tops.

I helped build with SAS R&D an automated Tops-Picker that ingests several well logs (*.las format: Vsh, GR and Neutron-Porosity,) performs ETL to impute missing values and clusters to predict major Tops for by-passed pay in brownfields. We are > 90% accurate and performed the prediction on 1100 wells across several clusters in 2 days compared to the 6 months the operator took for its petrophysicists to manually interpret.

Good work.

 

Keith

Version history
Last update:
‎10-20-2022 12:13 PM
Updated by:

sas-innovate-2024.png

Available on demand!

Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.

 

Register now!

Article Tags