System and method for liquids correction in oil and gas predictive

1. A method, comprising:

receiving, from a remote computing device, a set of production information for a plurality of plays from a region, the set of production information directed to past production of a plurality of wells;

generating, by a computing system, an input data set based on the set of production information;

identifying, by the computing system, a first portion of the input data set comprising a first plurality of wells that requires correction by fitting one or more decline curves to the input data set, wherein each well of the first plurality of wells comprises a month of production data that misreported;

consolidating, by the computing system, the one or more decline curves into a new data set;

classifying, by the computing system, the one or more decline curves by identifying a second plurality of wells in the new data set, the second plurality of wells comprising a threshold amount of production information, the classifying comprising:

identifying a second portion of the input data set that does not require correction, the second portion of the input data set comprising the second plurality of wells,

generating an interpolated map residual from the new data set based on control points of the second plurality of wells,

generating a kernel density heat map from the new data set, the kernel density heat map representing a density of the production data within a region of the second plurality of wells based on the control points,

generating a decline profile for the set of production information based on the interpolated map residual and the kernel density heat map,

imputing values for each month of the production data that misreported based on the decline profile, and

classifying the one or more decline curves based on the imputed values;

forecasting, by the computing system, future oil or gas production of the plurality of wells based on the classified one or more decline curves; and

delivering, by the computing system, the forecasted future oil or gas production of the plurality of wells to the remote computing device.

2. The method of claim 1 , wherein generating, by the computing system, the input data set comprises:

consolidating the set of production information for the plurality of plays into a single data set.

3. The method of claim 2 , further comprising:

identifying one or more missing days of data in the single data set;

generating a production value for each of the identified one or more missing days of data; and

imputing each production value in each respective missing day of data.

4. The method of claim 1 , wherein fitting, by the computing system, the one or more decline curves to the input data set comprises:

generating a confidence interval to identify the second portion of the input data set that exceeds the threshold amount of production value.

5. The method of claim 1 , identifying the second plurality of wells in the new data set comprises:

identifying in the new data set one or more values that comprise an r-squared value, a variance value, and a standard error value.

6. The method of claim 1 , wherein classifying, by the computing system, the one or more decline curves comprises:

partitioning the classified one or more decline curves into separate production profiles based on a respective play.

7. A system, comprising:

a processor; and

a memory having programming instructions stored thereon, which, when executed by the processor, performs an operation comprising:

receiving, from a remote computing device, a set of production information for a plurality of plays from a region, the set of production information directed to past production of a plurality of wells;

generating an input data set based on the set of production information;

identifying a first portion of the input data set comprising a first plurality of wells that requires correction by fitting one or more decline curves to the input data set, wherein each well of the first plurality of wells comprises a month of production data that misreported;

consolidating the one or more decline curves into a new data set;

classifying the one or more decline curves by identifying a second plurality of wells in the new data set, the second plurality of wells comprising a threshold amount of production information, the classifying comprising:

identifying a second portion of the input data set that does not require correction, the second portion of the input data set comprising the second plurality of wells,

generating an interpolated map residual from the new data set based on control points of the second plurality of wells,

generating a kernel density heat map from the new data set, the kernel density heat map representing a density of the production data within a region of the second plurality of wells based on the control points,

generating a decline profile for the set of production information based on the interpolated map residual and the kernel density heat map,

imputing values for each month of the production data that misreported based on the decline profile, and

classifying the one or more decline curves based on the imputed values; and

forecasting future oil or gas production of the plurality of wells based on the classified one or more decline curves; and

delivering the forecasted future oil or gas production of the plurality of wells to the remote computing device.

8. The system of claim 7 , wherein generating the input data set comprises:

consolidating the set of production information for the plurality of plays into a single data set.

9. The system of claim 8 , further comprising:

identifying one or more missing days of data in the single data set;

generating a production value for each of the identified one or more missing days of data; and

imputing each production value in each respective missing day of data.

10. The system of claim 7 , wherein fitting the one or more decline curves to the input data set comprises:

generating a confidence interval to identify the second portion of the input data set that exceeds the threshold amount of production value.

11. The system of claim 7 , identifying the second plurality of wells in the new data set comprises:

identifying in the new data set one or more values that comprise an r-squared value, a variance value, and a standard error value.

12. The system of claim 7 , wherein classifying the one or more decline curves comprises:

partitioning the classified one or more decline curves into separate production profiles based on a respective play.

13. 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 plurality of plays from a region, the set of production information directed to past production of a plurality of wells;

generating, by a computing system, an input data set based on the set of production information;

identifying, by the computing system, a first portion of the input data set comprising a first plurality of wells that requires correction by fitting one or more decline curves to the input data set, wherein each well of the first plurality of wells comprises a month of production data that misreported;

consolidating, by the computing system, the one or more decline curves into a new data set;

classifying, by the computing system, the one or more decline curves by identifying a second plurality of wells in the new data set, the second plurality of wells comprising a threshold amount of production information, the classifying comprising:

identifying a second portion of the input data set that does not require correction, the second portion of the input data set comprising the second plurality of wells,

generating an interpolated map residual from the new data set based on control points of the second plurality of wells,

generating a kernel density heat map from the new data set, the kernel density heat map representing a density of the production data within a region of the second plurality of wells based on the control points,

generating a decline profile for the set of production information based on the interpolated map residual and the kernel density heat map,

imputing values for each month of the production data that misreported based on the decline profile, and

classifying the one or more decline curves based on the imputed values;

forecasting, by the computing system, future oil or gas production of the plurality of wells based on the classified one or more decline curves; and

delivering, by the computing system, the forecasted future oil or gas production of the plurality of wells to the remote computing device.

14. The non-transitory computer readable medium of claim 13 , wherein generating, by the computing system, the input data set comprises:

consolidating the set of production information for the plurality of plays into a single data set.

15. The non-transitory computer readable medium of claim 14 , further comprising:

identifying one or more missing days of data in the single data set;

generating a production value for each of the identified one or more missing days of data; and

imputing each production value in each respective missing day of data.

16. The non-transitory computer readable medium of claim 13 , wherein fitting, by the computing system, the one or more decline curves to the input data set comprises:

generating a confidence interval to identify the second portion of the input data set that exceeds the threshold amount of production value.

17. The non-transitory computer readable medium of claim 13 , identifying the second plurality of wells in the new data set comprises:

identifying in the new data set one or more values that comprise an r-squared value, a variance value, and a standard error value.