Facies prediction along the wellbore using Machine Learning
Consultant/Trainer: Jaap Mondt
The Petrogenium (in collaboration with EPTS) Facies prediction along the wellbore using Machine Learning participants will gain a practical understanding of how Machine Learning is used to predict facies from well logs, learning the full workflow from data preparation to classification and regression tasks. They will experience hands-on exercises using open-source software to balance, standardize, and normalize datasets, then apply various ML algorithms such as Bayes, Logistic, Multilayer Perceptron, Support Vector, Nearest Neighbour, AdaBoost, and Trees for data classification.
Participants
This Petrogenium course aims at all those interested in understanding the impact Machine Learning will have on the Geosciences and then specifically the impact on facies prediction on log data. Hence, geologists, geophysicists and petroleum and reservoir engineers, involved in exploration and development of hydrocarbon fields.
Learning Objectives
At the end of the course participants will have a clear idea how Machine learning, being part of Artificial Intelligence will impact the future of Geosciences. This will be evident from the examples discussed. The course uses a mixture of lectures, practical exercises and direct (workshop-like) participant involvement in discussions.
Day 1
1. Welcome, Program, Biography,
2. Intro ML
3. ML Tutorial
4. ML Open Source Software
5. Weka
- Exercise 1 (Classification)
6. DNN
- Exercise 2 (Comparison Algorithms)
7. Activation Functions
8. Forward and Backward Propagation
- Videos: Geophysical Inversion versus ML, Deeplizard
- Exercise 3 (Very limited labelled data) & 4 (Regression algorithms)
9. ML Fluid Substitution
- Exercises 5 (Multilayer Perceptron Neural Networks)
10. Future of ML in Geophysics
Day 2
1. Summary Day 1
2. EM Inductive Sources, EM Grounded Sources
- Exercises 13-15
3. EM Natural Sources
- Exercises 16-18
4. EM GPR
- Videos: YouTube
- Exercises: 19-21
5. EM IP
- Exercises 22-26
6. Course Evaluation
Programme
Day 1
1. Welcome, Program, Biography,
2. Intro ML
3. ML Tutorial
4. ML Open Source Software
5. Weka
- Exercise 1 (Classification)
6. DNN
- Exercise 2 (Comparison Algorithms)
7. Activation Functions
8. Forward and Backward Propagation
- Videos: Geophysical Inversion versus ML, Deeplizard
- Exercise 3 (Very limited labelled data) & 4 (Regression algorithms)
9. ML Fluid Substitution
- Exercises 5 (Multilayer Perceptron Neural Networks)
10. Future of ML in Geophysics
Day 2
1. Summary Day 1
2. EM Inductive Sources, EM Grounded Sources
- Exercises 13-15
3. EM Natural Sources
- Exercises 16-18
4. EM GPR
- Videos: YouTube
- Exercises: 19-21
5. EM IP
- Exercises 22-26
6. Course Evaluation