A workflow for stochastic electrofacies classification from borehold depth data. The code is modularized so that different components can be replaced and modified easily.
The procedure used here involves a number of steps. Different settings can modify the workflow at each step.
- Preprocessing including normalization
- Principle component analysis to decorrelate the data
- Self organizing maps for initial classification
- Hierarchical clustering to obtain the multiscale classification
Check the main.m file for an example on how to use the code. The las reader has its own repository (https://github.com/MosGeo/LasToolbox)
Al Ibrahim, M. A., and Mukerji, T., 2015, Stochastic Multiscale Electrofacies Classification of Well Logs: A Case Study From North Slope, Alaska: Presented at the AAPG Annual Convention and Exhibition, Calgary, Alberta, Canada.