US 11,988,799 B2
System and method for liquids correction in oil and gas predictive
Norman Runciman, Calgary (CA); Morgan Kwan, Calgary (CA); Jiarao Huang, Calgary (CA); Jianan Qu, Calgary (CA); and Amanda Mackey, Calgary (CA)
Assigned to RS Energy Group Topco, Inc., Alberta (CA)
Filed by RS Energy Group Topco, Inc., Calgary (CA)
Filed on Jun. 12, 2020, as Appl. No. 16/899,890.
Claims priority of provisional application 62/962,458, filed on Jan. 17, 2020.
Prior Publication US 2021/0223430 A1, Jul. 22, 2021
Int. Cl. G01V 3/18 (2006.01); E21B 47/003 (2012.01); E21B 47/12 (2012.01); G06F 9/54 (2006.01); G06F 17/18 (2006.01); G06N 7/01 (2023.01)
CPC G01V 3/18 (2013.01) [E21B 47/003 (2020.05); E21B 47/12 (2013.01); G06F 9/545 (2013.01); G06F 17/18 (2013.01); G06N 7/01 (2023.01)] 17 Claims
OG exemplary drawing
 
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.