Method and system of producing hydrocarbons using physics-based data-driven inferred production

1. A method of predicting hydrocarbon production from one or more artificial lift wells, comprising:

obtaining measurements and/or well test data from the one or more artificial lift wells representing well performance at more than one time period, the measurements and/or well test data representing a fluid flow rate through a pump associated with the one or more artificial lift wells, wherein the fluid flow rate through the pump is determined using formula:

G ( gH,N,P,ρ,μ,Q,D,k )=0  (Eq. 1),

where H denotes a pump head, N is a pump speed (T −1 ), P is an electrical and/or mechanical power of the pump, g is a gravitational force, ρ is a fluid density, μ is a fluid viscosity, Q is the fluid flow rate through the pump, D is an impeller diameter of the pump, and k is a mean height of roughness in the pump;

obtaining a statistical model representing the well performance;

using the statistical model and the measurements and/or well test data, predicting real-time production of the one or more artificial lift wells and generating a measure of confidence;

identifying potential optimization opportunities for the well performance based on the predicted real-time production of the one or more artificial lift wells;

outputting the potential optimization opportunities; and

modifying hydrocarbon production activities using the potential optimization opportunities.

2. The method of claim 1 , further comprising:

generating the measure of confidence using the statistical model and the measurements and/or well test data; and

when the measure of confidence is greater than a pre-determined level, obtaining additional measurements and/or test data from the one or more artificial lift wells representing the well performance at an additional time period;

wherein the potential optimization opportunities are identified when the measure of confidence is less than the pre-determined level.

3. The method of claim 1 , wherein modifying the hydrocarbon production activities comprises modifying performance of one of the one or more artificial lift wells.

4. The method of claim 1 , wherein modifying the hydrocarbon production activities comprises one or more of modifying performance of the pump, well stimulation activities, well intervention activities, and well work-over activities.

5. The method of claim 4 , wherein the pump comprises an electric submersible pump or a progressing cavity pump.

6. The method of claim 1 , wherein predicting the real-time production comprises a machine learning-based formulation.

7. The method of claim 1 , further comprising:

storing the measurements and/or well test data from the more than one time period until the real-time production is predicted.

8. The method of claim 1 , wherein the measurements and/or well test data include one or more of the pump head, the pump speed, the electrical and/or mechanical power of the pump, the fluid density, the fluid viscosity, the impeller diameter of the pump, and the mean height of roughness in the pump associated with the one or more artificial lift wells.

9. A method of predicting hydrocarbon production from one or more artificial lift wells, comprising:

obtaining measurements and/or well test data from the one or more artificial lift wells representing well performance at more than one time period, the measurements and/or well test data representing a fluid flow rate through a pump associated with the one or more artificial lift wells, wherein the fluid flow rate through the pump is determined using formula:

G ( gH,N,P,ρ,μ,Q,D,k )=0  (Eq. 1),

where H denotes a pump head, N is a pump speed (T −1 ), P is an electrical and/or mechanical power of the pump, g is a gravitational force, ρ is a fluid density, μ is a fluid viscosity, Q is the fluid flow rate through the pump, D is an impeller diameter of the pump, and k is a mean height of roughness in the pump;

obtaining a statistical model representing the well performance;

using the statistical model and the measurements and/or well test data, predicting real-time production of the one or more artificial lift wells and generating a measure of confidence;

when the measure of confidence is greater than a pre-determined level, obtaining additional measurements and/or test data from the one or more artificial lift wells representing the well performance at an additional time period;

when the measure of confidence is less than the pre-determined level, identifying potential optimization opportunities for the well performance based on the predicted real-time production of the one or more artificial lift wells;

outputting the potential optimization opportunities; and

modifying hydrocarbon production activities using the potential optimization opportunities.

10. An apparatus for predicting production data from one or more artificial lift wells, comprising:

a processor;

an input device in communication with the processor and configured to receive input data comprising measurements and/or test data from the one or more artificial lift wells representing well performance at more than one time period, the measurements and/or well test data representing a fluid flow rate through a pump associated with the one or more artificial lift wells, wherein the fluid flow rate through the pump is determined using formula:

G ( gH,N,P,ρ,μ,Q,D,k )=0  (Eq. 1),

where H denotes a pump head, N is a pump speed (T −1 ), P is an electrical and/or mechanical power of the pump, g is a gravitational force, ρ is a fluid density, μ is a fluid viscosity, Q is the fluid flow rate through the pump, D is an impeller diameter of the pump, and k is a mean height of roughness in the pump;

a memory in communication with the processor, the memory having a set of instructions, wherein the set of instructions, when executed by the processor, are configured to:

obtain a statistical model representing the well performance;

using the statistical model and the measurements and/or well test data, predict real-time production of the one or more artificial lift wells and generate a measure of confidence;

when the measure of confidence is greater than a pre-determined level, obtain additional measurements and/or test data from the one or more artificial lift wells representing the well performance at an additional time period;

when the measure of confidence is less than the pre-determined level, identify potential optimization opportunities for the well performance based on the predicted real-time production of the one or more artificial lift wells; and

output the potential optimization opportunities so that hydrocarbon production activities may be modified using the potential optimization opportunities.

11. The apparatus of claim 10 , wherein the measurements and/or well test data include one or more of the pump head, the pump speed, the electrical and/or mechanical power of the pump, the fluid density, the fluid viscosity, the impeller diameter of the pump, and the mean height of roughness in the pump.

12. The apparatus of claim 11 , wherein the pump is an electric submersible pump or a progressing cavity pump.

13. A method of producing hydrocarbons from one or more artificial lift wells, comprising:

obtaining measurements and/or well test data from the one or more artificial lift wells representing well performance at more than one time period, the measurements and/or well test data representing a fluid flow rate through a pump associated with the one or more artificial lift wells, wherein the fluid flow rate through the pump is determined using formula:

G ( gH,N,P,ρ,μ,Q,D,k )=0  (Eq. 1),

where H denotes a pump head, N is a pump speed (T −1 ), P is an electrical and/or mechanical power of the pump, g is a gravitational force, ρ is a fluid density, μ is a fluid viscosity, Q is the fluid flow rate through the pump, D is an impeller diameter of the pump, and k is a mean height of roughness in the pump;

obtaining a statistical model of the one or more artificial lift wells, the statistical model representing the well performance of the one or more artificial lift wells;

using the statistical model and the measurements and/or well test data, predicting real-time production of the one or more artificial lift wells and generating a measure of confidence;

when the measure of confidence is greater than a pre-determined level, obtaining additional measurements and/or test data from the one or more artificial lift wells representing the well performance at an additional time period;

when the measure of confidence is less than the pre-determined level, identifying potential optimization opportunities for the well performance based on the predicted real-time production of the one or more artificial lift wells;

outputting the potential optimization opportunities; and

producing hydrocarbons from the one or more artificial lift wells using the potential optimization opportunities.

14. The method of claim 13 , wherein producing the hydrocarbons comprises modifying performance of the pump.

15. The method of claim 14 , wherein the pump comprises an electric submersible pump or a progressing cavity pump.

16. The method of claim 13 , wherein predicting the real-time production comprises a machine learning-based formulation.

17. The method of claim 13 , further comprising:

storing the measurements and/or well test data from the more than one time period until the real-time production is predicted.

18. The method of claim 13 , wherein the measurements and/or well test data include one or more of the pump head, the pump speed, the electrical and/or mechanical power of the pump, the fluid density, the fluid viscosity, the impeller diameter of the pump, and the mean height of roughness in the pump associated with the one or more artificial lift wells.