Synthetic Log Generation Package

Use ML models to generate synthetic well logs

Usage and Configuration

Run the workflows from this package to perform the calculations. The schedules may be adapted to use different contexts.

Follow the steps given in How do I configure packages pulled from Datagration's package repository to change the configuration of the package.

Details

Training the Model

The workflow Synthetic Log Generation: Train Model is used to train the machine learning model.

The models can be retrained whenever needed by running the schedule On Demand of workflow Synthetic Log Generation: Train Model .

Using the Model

The workflow Synthetic Log Generation: Predict is used to run predictions using the pre-trained model.

Currently only the neutron porosity is predicted.

Data Requirements

The following data is required:

bulk density
caliper
gamma ray
neutron porosity (for training the model)
resistivity deep
resistivity medium