Permeability Prediction Using Quadratic Discriminant Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining reservoir permeability are inadequate for accurately predicting system permeability under stress conditions, as they often overestimate permeability and are poorly suited for total system permeability prediction, especially when measurements are taken under surface conditions or from selected well intervals.
Innovation Solution
The use of geologic formation property logs from boreholes to apply clustering algorithms and quadratic discriminant analysis (QDA) to map permeability data points to clusters, enabling accurate prediction of system permeability by aggregating values from multiple boreholes and intervals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If core analysis measurements are taken under surface conditions, then permeability measurements can be obtained easily, but the measurements overestimate system permeability by an order of magnitude
Solution Approach 1:
The invention transforms the measurement approach by changing the physical conditions from surface conditions to in-situ stress conditions. This is achieved through applying confining pressure and effective stress to core samples, thereby changing the parameter state to match reservoir conditions and obtain accurate system permeability measurements.
2Reliability
If pressure transient analysis is performed over selected well intervals, then permeability measurements suitable for stimulation design can be obtained, but the measurements are poorly suited for total system permeability prediction
Solution Approach 1:
The invention creates a universal permeability measurement system that can serve multiple purposes. By measuring permeability under in-situ stress conditions representative of the entire reservoir, the system provides data applicable to both stimulation design for selected intervals and total system permeability prediction, eliminating the need for separate measurement methods.
3Measurement precision
If empirical and statistical techniques are used to predict formation permeability from wireline logs, then core permeability can be predicted effectively, but system permeability under stress conditions cannot be solved
Solution Approach 1:
The invention performs preliminary action by establishing a calibrated relationship between wireline log responses and in-situ permeability measurements obtained under stress conditions. This preliminary calibration enables subsequent prediction of system permeability from wireline logs without requiring complex empirical adjustments, as the baseline data already reflects true reservoir conditions.
Data Source
AI summary
Permeability prediction systems and methods using quadratic discriminant analysis are presented. At least one disclosed method embodiment includes: acquiring formation property measurements at a plurality of positions along at least one borehole in a study area; identifying clusters in a plurality of points representing the formation property measurements at the plurality of postions; and determining a system permeability value for each cluster. Quadratic Discriminant Analysis (“QDA”) is used to associate one the clusters with each position along the one or more boreholes, thereby determining a system permeability prediction for each position. The total system permeability can then be predicted by aggregating the system permeability predictions.