Part IV: Machine Learning & AI
Chapter 17
Supervised Learning — Prediction and Classification
schedule15 min readfitness_center5 exercises
infoWhat You'll Learn
- Implement regression models for continuous predictions
- Build classifiers for lithology and facies identification
- Master ensemble methods (Random Forest, XGBoost, LightGBM)
- Apply explainability tools (SHAP) to petroleum ML models
lightbulbDatasets Used in This Chapter
facies_classification.csvproduction_prediction.csv
Linear and Polynomial Regression
main.py
Decision Trees and Random Forests
main.py
Gradient Boosting (XGBoost, LightGBM)
main.py
Support Vector Machines
main.py
Lithofacies Classification
main.py
Model Explainability with SHAP
main.py
Exercises
fitness_center
Exercise 17.1Practice
Exercise 17.1
...
arrow_forward
codePythonSolve Nowarrow_forward
fitness_center
Exercise 17.2Practice
Exercise 17.2
...
arrow_forward
codePythonSolve Nowarrow_forward
fitness_center
Exercise 17.3Practice
Exercise 17.3
...
arrow_forward
codePythonSolve Nowarrow_forward
fitness_center
Exercise 17.4Practice
Exercise 17.4
...
arrow_forward
codePythonSolve Nowarrow_forward
fitness_center
Exercise 17.5Practice
Exercise 17.5
...
arrow_forward
codePythonSolve Nowarrow_forward