dilshad-geol/facies-classification-machine-learning

Facies Classification with vrious Machine Learning algorithms and result comparision

Facies classification is one of the most important tasks that geoscientists work on development and exploration projects. Sedimentary facies reflect particular physical, chemical, and biological condition that unit experienced during sedimentation process. To study these facies, rock samples are required. In this study, it is practiced to train various machine learning algorithms to predict facies from well log data. The dataset for this study comes from Hugoton and Panoma Fields in North America which was used in class exercise in The University of Kansas (Dubois et. al, 2007). It consists of log data of nine wells. We will use these log data to train supervised classifiers in order to predict discrete facies groups. All this implementation is based on scikit-learn libraries. These are:

1. Support vector machines (SVM)
2. Gaussian process classification (GPC)
3. Random forest classifier (RFC)
4. Multi-layer Perceptron classifier(Neural Network classifier, NNC)
5. K Nearest Neighbors Classifier (KNN)
6. Decision tree classifier (DT)
7. Logistic regression (LR)