Paradigm | - Paradigm SeisFacies Multi-attribute Classification Software

Careers

Home

My Asset

Solutions

Products

Support

Training

Resources

Company

Solutions | Reservoir Characterization | Reservoir Geophysics | Multi-attribute Classification

Solutions

Multi-attribute Classification

Related Content

Overview

Benefits

Features

Science

Modules

FAQ

Requirements

Paradigm™ SeisFacies^® supports the qualitative and quantitative assessment of explorative objects, and improves reservoir characterization within field development projects. It provides a set of tools and methodologies for multi-attribute classification and calibration of 2D and 3D seismic data.

SeisFacies is an integrated component of and extension to the Stratimagic^® classification methodologies for understanding and relating seismic response to reservoir variations.

Epos-based and standalone solutions
Principal Component Analysis: A technology for generating principal components that represent the heterogeneity of a multi-dimensional cloud
Multi-attribute Seismic Classification (blocks): Classifies all samples from a set of seismic attribute volumes over a user-specified interval, to produce a volume of classified samples.
Multi-attribute Map Classification: Classifies a user-specified set of seismic attribute maps by performing a clustering of the samples to produce an attribute facies map.
Multi-attribute Trace Classification: Classifies portions of traces extracted from a set of input seismic blocks to produce a seismic facies map.
Calibration: Mathematical operators, well property to seismic attribute relationships, and other user-defined formulas can be applied to data subsets to produce new volumes and/or maps.
Fusion: Mixes two attributes to create a single output (maps/volumes) based on a blend of the data according to value ranges.

Seisfacies classification showing a detailed distribution of facies within a reservoir

Extends the applicability scope of Stratimagic.
Results can be used to condition reservoir modeling, for better informed business decisions.
Integrated with Epos, SeisFacies provides a powerful solution for facies volume analysis.
Reduces noise and data redundancy, for a more effective interpretation.

Principal Component Analysis (PCA)
PCA is a statistical process used for data reduction. It identifies redundant information and keeps only uncorrelated information that contributes to a classification exercise. PCA analyzes the relationships between a rich set of attributes and extracts the principal elongation directions, to reduce the number of input variables. The user selects the number of principal components that are needed.

Brochures

Site Map