OpendTect Machine Learning supports supervised and unsupervised workflows for seismic facies analysis.

Today’s post discusses an unsupervised workflow. The 3D UVQ Waveform Segmentation workflow is the 3D variant of the Quick UVQ workflow that we discussed earlier in this series on OpendTect ML workflows. In Quick UVQ we segment (cluster) seismic waveforms (trace segments) around a mapped horizon into a user-defined number of segments. A typical number of segments in Quick UVQ is 10.

In 3D UVQ we cluster waveforms in a volume. The user-defined number of segments is much higher and typically around 50. The resulting waveform segmentation volume is easy to generate and is useful for seismic facies interpretation. A HorizonCube facilitates the interpretation as this allows visualizing patterns along chronostratigraphic events. The video shows how we slice through a waveform segmentation volume covering the Maui Field in New Zealand before explaining how the volume was generated.