M-Dimensional Attribute Vector Interpretation in Hydrocarbon Reservoirs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interpreting large datasets from subsurface formations is complex, especially when distributions are under-sampled or overlapping, and conventional methods are insufficient for distinguishing classes in higher-dimensional attribute spaces with limited petrophysical data.
Innovation Solution
A method for interpreting m-dimensional attribute vectors involves arranging vectors as points in attribute space, defining classes with classification points, postulating a classification rule, determining class-membership attributes with probabilistic membership values, and assigning display parameters for interactive updating and visualization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional cross-plotting methods are used to interpret attribute vectors, then two attributes can be visualized in 2D space, but the method becomes insufficient for distinguishing classes in higher-dimensional attribute spaces with three or more dimensions
Solution Approach 1:
The patent extends conventional 2D cross-plotting to m-dimensional attribute space (where m≥2), enabling visualization and classification of attributes beyond the traditional two-dimensional limit. This dimensional extension allows simultaneous interpretation of multiple attributes while maintaining the cross-plotting framework, resolving the contradiction between handling higher dimensions and method complexity.
2Measurement precision
If polygons are drawn to separate facies groups in cross-plots, then class discrimination can be achieved in 2D space, but the method is insufficient when distributions are under-sampled or overlapping and no or only few petrophysical data are available
Solution Approach 1:
The patent introduces probabilistic membership values that quantify the likelihood of each data point belonging to a particular class, replacing deterministic polygon boundaries. This parameter transformation from binary classification to probabilistic classification enables robust class discrimination even with under-sampled or overlapping distributions and limited petrophysical data.
3Reliability
If deterministic class boundaries are defined using polygons, then clear class separation can be achieved, but the method cannot handle under-sampled or overlapping distributions confidently
Solution Approach 1:
The patent implements an iterative process where probabilistic membership values are calculated and used to refine class definitions. The system provides feedback on the confidence level of each classification, allowing operators to identify areas where additional data or refined analysis is needed, thereby improving reliability without sacrificing operational ease.
Data Source
AI summary
A method for interpreting a plurality of m-dimensional attribute vectors (m2) assigned to a plurality of locations in an n-dimensional interpretation space (n1), which method comprises arranging at least a subset of the attribute vectors as points in an m-dimensional attribute space; defining k classes (k2) of attribute vectors by identifying for each class at least one classification point in attribute space; postulating a classification rule for points in attribute space; determining a class-membership attribute of a point in attribute space using the classification points and the classification rule to obtain a classified point; and assigning a display parameter to the classified point which is related to the class-membership attribute. In one embodiment the display parameter is a mixed display parameter derived from probabilistic membership values each representing a probability that the classified point belongs to a selected class. In another embodiment classified points are displayed in attribute space and in interpretation space at the same time. The method can be used in a method of producing hydrocarbons from a subsurface formation. Also provided are corresponding computer program products and computer systems.