Methods and Systems for Continuous Bottomhole Pressure Estimation

Abstract

A method of modeling borehole pressure (BHP) for a wellbore, comprising: receiving field data for the wellbore; training a machine learning (ML) classification model to determine a best physics correlation for BHP in the wellbore using a plurality of physics-based models; determining, using the ML classification model, the best physics correlation based on the field data for the wellbore; determining, using the best physics correlation, a BHP estimate based on the field data for the wellbore; training an ML regression model to determine a residual correction using the BHP estimate and the field data for the wellbore; and determining, using the ML regression model, a final BHP using the BHP estimate and the residual correction for the wellbore.

What is claimed is: 
     
         1 . A method of modeling bottomhole pressure (BHP) for a wellbore, comprising:
 receiving field data for the wellbore;   training a machine learning (ML) classification model to determine a best physics correlation for BHP in the wellbore using a plurality of physics-based models;   determining, using the ML classification model, the best physics correlation based on the field data for the wellbore;   determining, using the best physics correlation, a BHP estimate based on the field data for the wellbore;   training an ML regression model to determine a residual correction using the BHP estimate and the field data for the wellbore; and   determining, using the ML regression model, a final BHP using the BHP estimate and the residual correction for the wellbore.   
     
     
         2 . The method of  claim 1 , wherein the field data comprise static parameters and dynamic parameters. 
     
     
         3 . The method of  claim 2 , wherein the static parameters comprise pressure-volume-temperature (PVT) fluid properties and reservoir properties. 
     
     
         4 . The method of  claim 2 , wherein the dynamic parameters comprise multi-phase flow rate, wellhead pressure, gas to liquid ratio (GLR), and water cut (WCT). 
     
     
         5 . The method of  claim 1 , further comprising:
 determining the ML classification model selected from the group consisting of: an artificial neural network, a support vector machine, a fuzzy inference system, a flow regime classification, an expert system, and any combination thereof.   
     
     
         6 . The method of  claim 1 , wherein the ML regression model is selected from the group consisting of:
 an Ordinary Least Squares (OLS) model,   a Lasso model,   a support vector regression (SVR) model,   an Extreme Gradient Boosting (XGBoost) model, and any combination thereof.   
     
     
         7 . The method of  claim 1 , wherein the plurality of physics-based models comprise empirical models and mechanistic models for the wellbore. 
     
     
         8 . The method of  claim 1 , further comprising:
 validating the ML regression model using a median absolute percentage error (MedAPE) between actual BHP data and predicted BHP data for the wellbore.   
     
     
         9 . The method of  claim 1 , further comprising:
 performing, using the final BHP, one or more well performance forecasting methods to evaluate well production performance and optimize artificial lift designs for the wellbore, the one or more performance forecasting methods comprising at least one method selecting from the group consisting of: rate-transient analysis (RTA), history matching using reservoir simulation, and inflow-performance-relationship (IPR) estimation.   
     
     
         10 . The method of  claim 1 , wherein the best physics correlation is a multi-phase flow correlation. 
     
     
         11 . A system of modeling bottomhole pressure (BHP) for a wellbore, comprising:
 one or more processors; and   one or more computer-readable non-transitory storage media comprising instructions that, when executed by the one or more processors, cause one or more components of the system to perform operations comprising:   receiving field data for the wellbore;   training a machine learning (ML) classification model to determine a best physics correlation for BHP in the wellbore using a plurality of physics-based models;   determining, using the ML classification model, the best physics correlation based on the field data for the wellbore;   determining, using the best correlation, a BHP estimate based on the field data for the wellbore;   training an ML regression model to determine a residual correction using the BHP estimate and the field data for the wellbore; and   determining, using the ML regression model, a final BHP using the BHP estimate and the residual correction for the wellbore.   
     
     
         12 . The system of  claim 11 , wherein the field data comprise static parameters and dynamic parameters. 
     
     
         13 . The system of  claim 12 , wherein the static parameters comprise pressure-volume-temperature (PVT) fluid properties and reservoir properties. 
     
     
         14 . The system of  claim 12 , wherein the dynamic parameters comprise multi-phase flow rate, wellhead pressure, gas to liquid ratio (GLR), and water cut (WCT). 
     
     
         15 . The method of  claim 1 , further comprising:
 determining the ML classification model selected from the group consisting of: an artificial neural network, a support vector machine, a fuzzy inference system, a flow regime classification, an expert system, and any combination thereof.   
     
     
         16 . The system of  claim 11 , wherein the ML regression model is selected from the group consisting of:
 an Ordinary Least Squares (OLS) model,   a Lasso model,   a support vector regression (SVR) model,   an Extreme Gradient Boosting (XGBoost) model, and any combination thereof.   
     
     
         17 . The system of  claim 11 , wherein the plurality of physics-based models comprise empirical models and mechanistic models for the wellbore. 
     
     
         18 . The system of  claim 11 , further comprising:
 validating the ML regression model using a median absolute percentage error (MedAPE) between actual BHP data and predicted BHP data for the wellbore.   
     
     
         19 . The system of  claim 11 , further comprising:
 performing, using the final BHP, one or more well performance forecasting methods to evaluate well production performance and optimize artificial lift designs for the wellbore, the one or more performance forecasting methods at least one method selecting from the group consisting of:   rate-transient analysis (RTA), history matching using reservoir simulation, and inflow-performance-relationship (IPR) estimation.   
     
     
         20 . A non-transitory computer-readable medium comprising instructions that are configured, when executed by a processor, to perform operations comprising:
 receiving field data for the wellbore;   training a machine learning (ML) classification model to determine a best physics correlation for BHP in the wellbore using a plurality of physics-based models;   determining, using the ML classification model, the best physics correlation based on the field data for the wellbore;   determining, using the best physics correlation, a BHP estimate based on the field data for the wellbore;   training an ML regression model to determine a residual correction using the BHP estimate and the field data for the wellbore; and   determining, using the ML regression model, a final BHP using the BHP estimate and the residual correction for the wellbore.