Granted Patent B2

US 11,494,679 · App. 16/395,608 · Granted Nov 8, 2022

Inventors: Jingwen Zheng (Calgary, CA); Qi Zong (Calgary, CA); Stephen Michael Main (Calgary, CA)

Assignee: RS Energy Group Topco, Inc. CA

G06N5/048G06F30/20G06F2111/10

Abstract

Claims (67)

1. A method, comprising:

receiving, from a remote computing device, a set of production information for a well located in a region, the set of production information directed to past production of the well;

parsing the set of production information for the well to determine whether the set of production information for the well includes a threshold amount of production information;

upon determining that the set of production information for the well does not include the threshold amount of production information, identifying a pool of one or more reference wells from a plurality of reference wells, wherein each reference well in the plurality of reference wells comprises at least the threshold amount of production information;

selecting a subset of reference wells from the pool of one or more reference wells based on one or more traits of the well, the one or more traits comprising at least a calculated production information shape similarity factor;

generating a reference curve based on the set of production information associated with each reference well in the subset of reference wells; and

fitting a decline curve to the reference curve to determine an estimated ultimate recovery of the well.

2. The method of claim 1 , wherein identifying the pool of one or more reference wells from the plurality of reference wells, comprises:

identifying one or more reference wells with similarities to the well that comprise at least the threshold amount of production information.

3. The method of claim 2 , wherein identifying the one or more reference wells with similarities to the well that comprise at least the threshold amount of production information comprises:

identifying the subset of reference wells in the pool of one or more reference wells based on reference wells that comprise production information most similar to the set of production information of the well.

4. The method of claim 3 , wherein generating the reference curve based on the set of production information associated with each reference well in the subset of reference wells, comprises:

identifying data associated with each reference well in the subset of reference wells;

averaging the data associated with each reference well in the subset of reference wells; and

generating the reference curve based on the averaged data for each reference well in the subset of reference wells.

5. The method of claim 1 , wherein identifying the pool of one or more reference wells from the plurality of reference wells, comprises:

identifying a predefined number of reference wells based on a hierarchical level of granularity.

6. The method of claim 5 , further comprising:

upon receiving the set of production information for the well located in the region, pre-processing the set of production information by:

removing one or more outliers from the set of production information as well as downtime and other variations of data anomalies that could affect analytic conclusions; and

normalizing the set of production information.

7. The method of claim 1 , wherein the threshold amount of production information comprises at least fifteen months of production information or any user defined number.

8. A system, comprising:

a processor; and

a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:

receiving, from a remote computing device, a set of production information for a well located in a region, the set of production information directed to past production of the well;

parsing the set of production information for the well to determine whether the set of production information for the well includes a threshold amount of production information;

upon determining that the set of production information for the well does not include the threshold amount of production information, identifying a pool of one or more reference wells from a plurality of reference wells, wherein each reference well in the plurality of reference wells comprises at least the threshold amount of production information;

selecting a subset of reference wells from the pool of one or more reference wells based on one or more traits of the well, the one or more traits comprising at least a calculated production information shape similarity factor;

generating a reference curve based on the set of production information associated with each reference well in the subset of reference wells; and

fitting a decline curve to the reference curve to determine an estimated ultimate recovery of the well.

9. The system of claim 8 , wherein identifying the pool of one or more reference wells from the plurality of reference wells, comprises:

identifying one or more reference wells with similarities to the well that comprise at least the threshold amount of production information.

10. The system of claim 9 , wherein identifying the one or more reference wells with similarities to the well that comprise at least the threshold amount of production information comprises:

identifying the subset of reference wells in the pool of one or more reference wells based on reference wells that comprise production information most similar to the set of production information of the well.

11. The system of claim 10 , wherein generating the reference curve based on the set of production information associated with each reference well in the subset of reference wells, comprises:

identifying data associated with each reference well in the subset of reference wells;

averaging the data associated with each reference well in the subset of reference wells; and

generating the reference curve based on the averaged data for each reference well in the subset of reference wells.

12. The system of claim 8 , wherein identifying the pool of one or more reference wells from the plurality of reference wells, comprises:

identifying a predefined number of reference wells based on a hierarchical level of granularity.

13. The system of claim 12 , further comprising:

upon receiving the set of production information for the well located in the region, pre-processing the set of production information by:

removing one or more outliers from the set of production information as well as downtime and other variations of data anomalies that could affect analytic conclusions; and

normalizing the set of production information.

14. The system of claim 8 , wherein the threshold amount of production information comprises at least fifteen months of production information.

15. A non-transitory computer readable medium having instructions stored thereon, which, when executed by a processor, cause the processor to perform a method, comprising:

receiving, from a remote computing device, a set of production information for a well located in a region, the set of production information directed to past production of the well;

parsing the set of production information for the well to determine whether the set of production information for the well includes a threshold amount of production information;

upon determining that the set of production information for the well does not include the threshold amount of production information, identifying a pool of one or more reference wells from a plurality of reference wells, wherein each reference well in the plurality of reference wells comprises at least the threshold amount of production information;

selecting a subset of reference wells from the pool of one or more reference wells based on one or more traits of the well, the one or more traits comprising at least a calculated production information shape similarity factor;

generating a reference curve based on the set of production information associated with each reference well in the subset of reference wells; and

fitting a decline curve to the reference curve to determine an estimated ultimate recovery of the well.

16. The non-transitory computer readable medium of claim 15 , wherein identifying the pool of one or more reference wells from the plurality of reference wells, comprises:

identifying one or more reference wells with similarities to the well that comprise at least the threshold amount of production information.

17. The non-transitory computer readable medium of claim 16 , wherein identifying the one or more reference wells with similarities to the well that comprise at least the threshold amount of production information comprises:

identifying the subset of reference wells in the pool of one or more reference wells based on reference wells that comprise production information most similar to the set of production information of the well.

18. The non-transitory computer readable medium of claim 17 , wherein generating the reference curve based on the set of production information associated with each reference well in the subset of reference wells, comprises:

identifying data associated with each reference well in the subset of reference wells;

averaging the data associated with each reference well in the subset of reference wells; and

generating the reference curve based on the averaged data for each reference well in the subset of reference wells.

19. The non-transitory computer readable medium of claim 15 , wherein identifying the pool of one or more reference wells from the plurality of reference wells, comprises:

identifying a predefined number of reference wells based on a hierarchical level of granularity.

20. The non-transitory computer readable medium of claim 19 , further comprising:

upon receiving the set of production information for the well located in the region, pre-processing the set of production information by:

removing one or more outliers from the set of production information as well as downtime and other variations of data anomalies that could affect analytic conclusions; and

normalizing the set of production information.

Assignments (9)

Continuity (2)