Show button Hide button Support

Facies Classification

Integration of Facies Classification into the Interpretation Suite 

A unique way to gain a deeper understanding of data through facies analysis.

Facies classification includes techniques used in stratigraphic interpretation to extract geological information from seismic data associated with rock types, depositional environments, fluid content, etc.

Facies Classification Benefits

  • Easy-to-use workflow guided interface 
  • Extract geological information from seismic data
  • Understand lateral and vertical distribution of seismic facies
  • Predict rock type distribution away from well control
  • Capture uncertainty of predictions

Facies Classification Features

  • Supervised classification for rock type prediction using machine learning
  • Supervised classification for rock type prediction using a deterministic crossplot based method
  • Several machine learning methods for unsupervised classification of volumes and maps 
  • Principal Component Analysis workflow to analyze relationships between different attributes and create new attributes that capture main information 
  • Access to parameter testing for sensitivity analysis 
  • Report of workflow capturing input data, parameters and statistics
  • Workflow automation with chain workflows and workflow re-play



SeisEarth facies classification tools and methods include machine learning algorithms, crossplot-based methods and options for data dimensionality analysis and reduction.

Machine Learning-based Classification Workflows

Waveform Classification*

Waveform Classification uses the same proven neural network method as used in Stratimagic for classifying seismic wave shapes. The implementation of this methodology as a plug-in to SeisEarth provides access to quality control tools as well as advanced wave shape constraining from the 2D Wedge Modeling utility, to map the impact of changes in reservoir conditions on amplitude data.  For example, users may map thickness variations or fluid effects on seismic data by constraining seismic facies mapping with synthetic traces representing those effects. With such an embedded workflow, the geoscientist can perform the calibration of waveform classification to different scenarios, and play the “what if” game to evaluate prospects.  

In a 4D analysis context, waveform classification models help to compare the seismic response between two different seismic vintages. This provides an easy way to analyze how the the seismic response evolves through time, as a result of hydrocarbon production and/or fluid injection.

* Developed by Total

Map Classification

Map Classification uses the same proven neural network method as used in Stratimagic to perform facies classification of maps. The methodology, provided as a plug-in to SeisEarth, enables access to an interval attribute workflow chained with map classification, the output of which (several maps) can be used as input for map classification. 

Attribute Clustering

Attribute clustering is an unsupervised classification method which extends Machine Learning beyond facies analysis to other uses, including: 

  • Structural delineation from multiple seismic attributes
  • AVO analysis from prestack data and AVO attributes
  • Outlier detection 

Rock Type Classification

Winner of Hart Energy’s Meritorious Awards for Engineering Innovation (MEAs) in Exploration/Geoscience

Click here to learn more about Rock Type classification.

The Rock Type Classification workflow uses a brand new algorithm to generate rock type volumes calibrated to facies logs using a probabilistic approach, to assess uncertainty in rock type distribution.  Users have the option to access the Rock Type Classification workflow directly within the interpretation platform.  The probabilistic approach results in less guesswork when quantifying uncertainty. Results are interactively displayed in a 2D and 3D visualization system for in-depth analysis and downstream usage, for instance in geobody-picking workflows and well planning.

Rock Type Classification Benefits:

  • Enables better risk management and well planning optimization
  • Brings new potential about seismic data reliability when predicting reservoir facies away from wells, especially when referring to prestack data, which carry more information with any type of seismic attributes.
  • Allows the faster creation of predictive analyses of the subsurface while still maintaining accuracy, thus helping to accelerate the decision-making process when determining the drilling location.

Crossplot-based Methods

Lithoseismic Classification

Lithoseismic classification is a crossplot based method between two input attributes that enables the estimation of facies probability volumes and most probable lithofacies.

Dimensionality Reduction

Principal Component Analysis

A mathematical transformation that can be used to extract key information from multiple volumes so the interpreter can reduce data dimensionality without sacrificing information, the analysis also gives insights about how attributes related to each other and identification of which attributes provide unique information.