🐙 GitHub Detail
syedmamir/Geological-Log-Data-Machine-Learning-with-Python
By syedmamir
A geological log data from a well in Kansas, USA is analyzed using Machine Learning (M.L.) techniques in Python. The data is overviewed, cleaned and analyzed for important patterns and relationships with which we found relationships of logs with each other and correlation of types of formations with the logs. Using this, we can eliminate the use...
A geological log data from a well in Kansas, USA is analyzed using Machine Learning (M.L.) techniques in Python. The data is overviewed, cleaned and analyzed for important patterns and relationships with which we found relationships of logs with each other and correlation of types of formations with the logs. Using this, we can eliminate the use of logs which are correlated or have no relative importance to the type of formation when we have prior geological knowledge of the area. Also, predictions of formation type were made successfully once the data is trained with the M.L. algorithms.
Live Snapshot
⭐
Stars
15
🍴
Forks
5
📄
License
Unknown
🧩
Type
Jupyter Notebook
About this open-source project
Live information fetched from GitHub.
A geological log data from a well in Kansas, USA is analyzed using Machine Learning (M.L.) techniques in Python. The data is overviewed, cleaned and analyzed for important patterns and relationships with which we found relationships of logs with each other and correlation of types of formations with the logs. Using this, we can eliminate the use...
A geological log data from a well in Kansas, USA is analyzed using Machine Learning (M.L.) techniques in Python. The data is overviewed, cleaned and analyzed for important patterns and relationships with which we found relationships of logs with each other and correlation of types of formations with the logs. Using this, we can eliminate the use of logs which are correlated or have no relative importance to the type of formation when we have prior geological knowledge of the area. Also, predictions of formation type were made successfully once the data is trained with the M.L. algorithms.
Default Branch
master
Open Issues
0
Watchers
15