ML Petrophysical Prediction

Description Predict volumetric composition ratios for petrophysical components at different depth samples using a trained machine learning model.
Module(s) Lithofluids

This process accepts up to nine input curves corresponding to different measurement types and returns volumetric composition ratios for seven different components at each depth sample, as predicted by DUG Insight's Machine Learning model.

The accuracy of the model is highly dependent on the quality of the input curves.

  1. In the Control Panel, go to View > New Single Well View.
  2. In the Single Well window, open the Process tab.
  3. At the tab header, click the blue "+" icon.
  4. Click ML Petrophysical Prediction.
  5. Type a name for the process and click OK.
  1. Input
    • Curves: Select the relevant input curves.
  2. Output
    • Enable custom name: If enabled, the specified name is appended to the output curve names. The custom name should be unique for each ML Petrophysical Prediction process.
    • Extent: Determines the sampling grid for the output curves. All input data is resampled onto the output grid before being passed through the inference model.

Note: The output curves of the ML Petrophysical Prediction process are placed in individual data classes named "Volume (lithology)" in the Curves tab.

Display the Volumetric Composition Ratios as Stacked Fills

Visualise the result by displaying the output curves as stacked fills on a single track:

  1. In the Process tab, right-click the ML Petrophysical Prediction process, and select Add outputs to new Stacked Fill Track.
  2. A stacked fill curve containing all probability curves is displayed in a new track.

For more configuration details, refer to Stacked Fill Curves.