Machine Learning Environment

Facies Classification

ML techniques can deliver significant benefits for facies classification. Facies clusters defined for a play using unsupervised analysis on a few selected wells can be applied rapidly via supervised classification to large numbers of wells across the play, bringing new scale and accuracy to these activities.

 

For unsupervised facies classification, PowerLog Python Extensions let you run ML algorithms using a workflow that:

 

  • Includes sub-facies clustering and data analysis for choosing an optimum number of clusters
  • Can access all data in the database for selected projects and wells
  • Generates the facies and produces a series of analytical plots for assigning the unsupervised facies
  • Enables geoscientists to generate high-quality facies logs on multiple wells simultaneously

 

Generate Missing Curves (Delta T Shear)

Shear Velocity is often required for seismic modeling, and accurate modeling of missing Delta T Shear curves is a critical part of the process. DL workflows can help you predict these missing curves.

 

You can easily adapt the workflows provided by GeoSoftware to meet your specific needs. In addition, Python-knowledgeable interpreters can build custom DL workflows. You can also take advantage of open-source Python utilities and programs, which include hundreds of scientific calculations, data analysis, and visualization libraries and programs.