DATA FUSION TECHNIQUE TO COMPUTE RESERVOIR QUALITY AND COMPLETION QUALITY BY COMBINING VARIOUS LOG MEASUREMENTS

• US 20190331813A1
• Filed: 04/30/2018
• Published: 10/31/2019
• Est. Priority Date: 04/30/2018
• Status: Active Grant

• Current Assignee: Schlumberger Technology Corporation (SLB)
• Original Assignee: Schlumberger Technology Corporation (SLB)
• Inventors: Zhang, Tuanfeng, Lewis, Richard E., Gamero Diaz, Helena
• Granted Patent: US 11,112,516 B2
• Time in Patent Office: Days
• CPC Class Codes: G01V 1/30 Analysis G01V1/50 takes precedence
• CPC Class Codes: G01V 1/40 specially adapted for well-logging
• CPC Class Codes: G01V 2210/61 Analysis by combining or comparing a seismic data set with other data
• CPC Class Codes: G06F 17/153 Multidimensional correlation or convolution
• CPC Class Codes: G06F 17/16 Matrix or vector computation , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization matrix transposition G06F7/78
• CPC Class Codes: G06F 18/2135 based on approximation criteria, e.g. principal component analysis
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Methods may include normalizing two or more wellbore logs obtained from the output of two or more wellbore tool surveys of a wellbore in a formation of interest; inputting two or more wellbore logs into a correlation matrix; assigning each of the two or more wellbore logs a positive or negative value based on the impact on a selected wellbore quality; performing a principal component analysis of the two or more wellbore logs to obtain one or more loading vectors; computing weighting factors for each of the two or more wellbore logs from the one or more loading vectors; and generating a quality index by linearly combining the two or more wellbore logs using the computed weighting factors.

Claims

1. A method, comprising:

normalizing two or more wellbore logs obtained from the output of two or more wellbore tool surveys of a wellbore in a formation of interest;

inputting two or more wellbore logs into a correlation matrix;

assigning each of the two or more wellbore logs a positive or negative value based on the impact on a selected wellbore quality;

performing a principal component analysis of the two or more wellbore logs to obtain one or more loading vectors;

computing weighting factors for each of the two or more wellbore logs from the one or more loading vectors; and

generating a quality index by linearly combining the two or more wellbore logs using the computed weighting factors.

2. The method of claim 1, further comprising:

inputting a user-defined threshold for the selected quality being indexed.

3. The method of claim 2, wherein the quality index is a reservoir quality log and wherein the method further comprises:

designating one or more wellbore intervals in a reservoir quality log as pay regions based on the user-defined threshold.

4. The method of claim 3, further comprising:

transitioning the wellbore to production and producing hydrocarbons from the one or more wellbore intervals designated as pay regions.

5. The method of claim 3, wherein the two or more wellbore logs are selected from a group consisting of:

gamma ray, deep resistivity, bulk rock density, and thermal neutron porosity.

6. The method of claim 2, wherein the quality index is a completion quality log, and wherein the method further comprises:

designating one or more regions in the completion quality log as completion targets.

7. The method of claim 6, further comprising:

completing one or more regions designated as completion targets.

8. The method of claim 6, wherein the two or more wellbore logs are selected from a group consisting of:

clay, pyrite, quartz-feldspar-mica, and total organic carbon.

9. The method of claim 1, wherein computing weighting factors for each of the two or more wellbore logs comprises analyzing each of the wellbore logs with a Kriging estimator that analyzes the loading vectors of the wellbore logs from the principal component analysis.

10. The method of claim 1, further comprising:

performing interpolation or mapping of the quality index in 3D.

11. The method of claim 2, wherein the user-defined threshold is optimized to minimize the misclassification rate of one or more wellbore intervals in the quality log.

12. The method of claim 11, wherein the optimized threshold is applied to quality logs obtained from other wells.

13. A method, comprising:

normalizing two or more wellbore logs obtained from the output of two or more wellbore tool surveys of a wellbore in a formation of interest;

inputting two or more wellbore logs into a correlation matrix;

assigning each of the two or more wellbore logs a positive or negative sign based on the impact on a selected wellbore quality;

performing a principal component analysis of the two or more wellbore logs to obtain one or more loading vectors;

computing weighting factors for each of the two or more wellbore logs from the one or more loading vectors;

generating a reservoir quality log by linearly combining the two or more wellbore logs using the computed weighting factors;

generating a completion quality log by linearly combining the two or more wellbore logs using the computed weighting factors; and

preparing a composite reservoir quality index from the product of the reservoir quality log and the completion quality log.

14. The method of claim 13, further comprising:

inputting a user-defined threshold for the composite reservoir quality log.

15. The method of claim 14, wherein the method further comprises:

designating one or more wellbore intervals in a composite reservoir quality log as regions of interest based on the user-defined threshold.

16. The method of claim 15, further comprising:

transitioning the wellbore to production or completion and producing hydrocarbons from or completing the one or more wellbore intervals designated as regions of interest.

17. The method of claim 13, wherein the two or more wellbore logs are selected from a group consisting of:

gamma ray, deep resistivity, bulk rock density, thermal neutron porosity, clay, pyrite, quartz-feldspar-mica, and total organic carbon.

18. The method of claim 13, wherein computing weighting factors for each of the two or more wellbore logs comprises analyzing each of the wellbore logs with a Kriging estimator that analyzes the loading vectors of the wellbore logs from the principal component analysis.

19. The method of claim 13, further comprising performing interpolation or mapping of the composite reservoir quality index in 3D.

20. The method of claim 14, wherein the user-defined threshold is optimized to minimize the misclassification rate of one or more wellbore intervals in the composite reservoir quality log.