Facies Modeling
in some cases, a deterministic Impedance based Inversion process may not be suitable. Reasons for this could Include:
- Poor quality well and/or seismic data, e.g. high random noise content; weak reflectors.
- Lack of resolution, e.g. deep targets with insufficient vertical or lateral resolution and aperture.
- No separation of rock and fluid properties In the elastic domains. (Modeling can help predict this prior to beginning an expensive AVO or Impedance Inversion.)
In such cases, we offer a multi-attribute neural network workflow, designed to provide seismic faces descriptions calibrated to well-data. Workflow elements Include:
Attribute Computation
A variety of seismic attribute volumes can be computed using Attrib3D. Relative acoustic Impedance and seismic waveform attributes may be added depending on the geological setting and project objective.
Statistical Multi-Attribute Neural Network analysis
The Individual attribute volumes are combined into a single output using RSI’s unsupervised neural network classifier. A 2D rectangular Kohonen topology is employed. Calibration of classes is performed at well-locations where known faces are sampled. The output classes are combined and re-numbered to yield a calibrated seismic fa. volume. The resulting 3D seismic facies volume is examined within a powerful 3D visualization system to yield geological interpretations of the subsurface structure and properties.