Petrophysics - Applications of Machine Learning to Petrophysical Workflows
Vložit
- čas přidán 23. 07. 2024
- The adoption of machine learning within the petrophysics domain has increased greatly over the past decade. This short presentation looks at what Machine Learning is and how it is being applied to petrophysics.
If you haven't already, make sure you subscribe to the channel: / @andymcdonald42
If you have enjoyed this video and want to say thanks, feel free to buy me a coffee at the following link: buymeacoffee.com/andymcdonaldgeo
-----
Books I Recommend:
As an Amazon Associate I earn from qualifying purchases. By buying through any of the links below I will earn commission at no extra cost to you.
PYTHON FOR DATA ANALYSIS: Data Wrangling with Pandas, NumPy, and IPython
UK: amzn.to/3HNycJ9
US: amzn.to/3DL7qPv
FUNDAMENTALS OF PETROPHYSICS
UK: amzn.to/3l1PgSf
PETROPHYSICS: Theory and Practice of Measuring Reservoir Rock and Fluid Transport Properties
UK: amzn.to/30UNWZS
US: amzn.to/3DNqBbd
WELL LOGGING FOR EARTH SCIENTISTS
UK: amzn.to/3FHsbfn
US: amzn.to/3CILAuE
GEOLOGICAL INTERPRETATION OF WELL LOGS
UK: amzn.to/3l2v2HV
US: amzn.to/30UOTkU
-----
Thanks for watching, if you want to connect you can find me at the links below:
/ andymcdonaldgeo
/ geoandymcd
/ andymcdonaldgeo
www.andymcdonald.scot/
Be sure to sign up to my newsletter to be kept updated when I post and share new content on CZcams and Medium.
www.getrevue.co/profile/andym...
#petrophysics #machinelearning #geoscience
Chapters
0:00 Introduction
1:19 Where Does Machine Learning Fit In?
2:28 Machine Learning vs Traditional Programming
3:06 Petrophysics and Machine Learning Publications (2010-2021)
4:04 Machine Learning Types
6:34 Applications of Machine Learning to Petrophysics
7:29 Outlier Detection
9:14 Well Log Repair
10:08 Well Log Normalisation
12:19 Missing Data Prediction
14:12 Well Log Correlation
14:56 Depth Alignment
15:54 Continuous Data From Discrete Data
17:31 Facies Classification (Unsupervised)
18:50 Petrophysical Property Prediction - Věda a technologie
Thank you for this. You just helped me narrow down all I need for my project.
Glad I could help!
Great video Andy! Very good of you to put it together.
Thanks Mark
Thank you for including all the references!
No problem! I will update the comments section with direct links to them in the next few days
I like the K mean clustering techniques in which it manage to demonstrate the similarity/difference on the stratigraphy. May i know how to write the script for calculating the thickness of each of the category?
Very informative session indeed. Thanks for sharing...
Glad you enjoyed it Vinay!
Hope you make more videos on this topic. I still want to know how to interpret the outliers. Really good video !!!
I will be. What aspect of outliers in log data is it you are looking for more info on? One of my next medium articles will look at outlier detection with ML algorithms and boxplots. Is this along the lines of what you are thinking, or is it more well log interpretation (e.g caliper is washed out, therefore the density may read low)
Amazing Video, thanks!
You're welcome! :)
Thank you for sharing this information with us
It well be great if you go deeper in the applications
No problem Mohammed. I will be having a closer look at a few of the methods in the future.
Very informative video. thank you very much for sharing these informations.
Hope you show us an ML example with las files.
I will do. It is on the list for future videos.
Really good video, Could you please make a detailed video on the prediction of mission logs using ML?
Keep up the good work.
Thanks. That is on the list of upcoming videos.
Thank you, It was a really great video, Can you make a complete playlist, for machine learning from basics to advanced training within the petrophysics domain? No one has done it. It would be really really helpful. Thank you again
Great suggestion! I do have a playlist which focuses on a few algorithms with petrophysical data:
czcams.com/play/PLv6Xu6O6acN7YCmPB3U3WubBP2KUY4bS4.html
I am planning to expand this playlist or turn it into a course in the future.