Permeability prediction systems and methods using quadratic discriminant analysis

Patent metadata

Field	Value
Publication number	US-9176255-B2
Application number	US-201114362358-A
Country	US
Kind code	B2
Filing date	Dec 8, 2011
Priority date	Dec 8, 2011
Publication date	Nov 3, 2015
Grant date	Nov 3, 2015

Abstract

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.

First claim

What is claimed is:

1. A method for predicting total system permeability of a geologic formation, comprising:
acquiring formation property measurements at a plurality of positions along at least one borehole in the geologic formation;
identifying clusters in a plurality of points representing the formation property measurements at the plurality of postions;
determining a system permeability value for each cluster;
applying Quadratic Discriminant Analysis (“QDA”) to associate each of multiple positions in one or more boreholes with a corresponding cluster based on formation property measurements, thereby obtaining a system permeability prediction for each of said multiple positions; and
predicting total system permeability based at least in part on an aggregation of the system permeability predictions for each of said multiple positions.

2. The method of claim 1 , wherein said determining includes:
employing pressure transient tests to obtain system permeability measurements over multiple intervals in the at least one borehole.

3. The method of claim 2 , wherein said determining further includes:
associating a system permeability measurement with each of said plurality of points representing positions in an interval from which the system permeability measurement was obtained; and
combining the system permeability measurements associated with the points in a given cluster to determine the system permeability value for that cluster.

4. The method of claim 3 , wherein said combining includes averaging.

5. The method of claim 3 , wherein said combining includes applying a statistical analysis across the clusters to isolate the contributions of each cluster to the obtained system permeability measurements.

6. The method of claim 1 , wherein said determining includes:
employing diagnostic fracture injection testing (DFIT) to obtain system permeability measurements corresponding to individual points; and
averaging the system permeability measurements associated with points in a given cluster to determine the system permeability value for that cluster.

7. The method of claim 1 , wherein said determining includes:
employing core sample permeability measurements to estimate system permeability measurements corresponding to individual points; and
averaging the estimated system permeability measurements associated with points in a given cluster to determine the system permeability value for that cluster.

8. The method of claim 1 , wherein said identifying includes:
employing a k-means clustering technique to determine an optimum number of clusters; and
finding a k-means clustering solution having the optimum number of clusters.

9. The method of claim 1 , wherein said identifying includes basing coordinates for the plurality of points on normalized formation property measurements.

10. A system for predicting total system permeability of a geologic formation, comprising:
a memory that stores total system permeability prediction software;
at least one processor coupled to the memory to execute the software, wherein the software configures the processor to:
acquire formation property measurements at a plurality of positions along at least one borehole in the geologic formation;
identify clusters in a plurality of points representing the formation property measurements at the plurality of postions;
determine a system permeability value for each cluster;
apply Quadratic Discriminant Analysis (“QDA”) to associate each of multiple positions in one or more boreholes with a corresponding cluster based on formation property measurements, thereby obtaining a system permeability prediction for each of said multiple positions;
predict total system permeability based at least in part on an aggregation of the system permeability predictions for each of said multiple positions; and
display the predicted total system permeability.

11. The system of claim 10 , wherein as part of said determining, the software configures the at least one processor to employ pressure transient test results to obtain system permeability measurements over multiple intervals in the at least one borehole.

12. The system of claim 11 , wherein as part of said determining the software further configures the at least one processor to:
associate a system permeability measurement with those points representing positions in an interval from which the system permeability measurement was obtained; and
combine the system permeability measurements associated with the points in a given cluster to determine the system permeability value for that cluster.

13. The system of claim 12 , wherein as part of said combining the software configures the at least one processor to average the system permeability measurements associated with points in a given cluster.

14. The system of claim 12 , wherein as part of said combining the software configures the at least one processor to apply a statistical analysis across the clusters to isolate contributions of each cluster to the obtained system permeability measurements.

15. The system of claim 10 , wherein as part of said determining, the software configures the at least one processor to:
employ results of diagnostic fracture injection testing (DFIT) to obtain system permeability measurements corresponding to individual points; and
average the system permeability measurements associated with points in a given cluster to determine the system permeability value for that cluster.

16. The system of claim 10 , wherein as part of said determining, the software configures the at least one processor to:
estimate system permeability measurements corresponding to individual points based on core sample permeability measurements; and
average the estimated system permeability measurements associated with points in a given cluster to determine the system permeability value for that cluster.

17. The system of claim 10 , wherein as part of said identifying, the software configures the at least one processor to:
determine an optimum number of clusters using a k-means clustering technique; and
find a k-means clustering solution having the optimum number of clusters.

18. The system of claim 10 , wherein as part of said identifying, the software configures the at least one processor to normalize the formation property measurements and use the normalized formation property measurements as coordinates for the plurality of points.

Assignees

• Wiener Jacky M
• Ramurthy Muthukumarappan
• Halliburton Energy Services Inc

Inventors

• Wiener Jacky M
• Ramurthy Muthukumarappan

Classifications

• E21B49/008

  by injection test; by analysing pressure variations in an injection or production test, e.g. for estimating the skin factor (measuring pressure E21B47/06) · CPC title

• G01V2210/6246

  Permeability · CPC title

• G01V99/00 Primary

  Subject matter not provided for in other groups of this subclass · CPC title

• E21B49/02

  by mechanically taking samples of the soil · CPC title

• G01V1/50 Primary

  Analysing data · CPC title