Guidance and event prediction for well drilling operations

Abstract

A method for use with a subterranean well drilling operation can include training a predictive model with historical well data to predict a probability of a historical wellbore event occurring, then inputting to the trained predictive model parameters of a target well to be drilled, and the predictive model predicting a probability of a wellbore event occurring in the target well. A system for use with a subterranean well drilling operation can include a predictive model trained to predict at least one historical wellbore event, based on historical well data. The predictive model can be configured to predict a probability of a wellbore event occurring in a target well. The predictive model can be configured to provide guidance for drilling the target well.

What is claimed is: 
     
         1 . A method for use with a subterranean well drilling operation, the method comprising:
 training a predictive model with historical well data to predict a probability of a historical wellbore event occurring;   then inputting to the trained predictive model parameters of a target well to be drilled; and   the predictive model predicting a probability of a wellbore event occurring in the target well.   
     
     
         2 . The method of  claim 1 , in which the historical well data comprises data recorded for at least one offset well. 
     
     
         3 . The method of  claim 1 , in which the predictive model comprises artificial intelligence. 
     
     
         4 . The method of  claim 1 , in which the predicting comprises providing geomechanics principles to the predictive model. 
     
     
         5 . The method of  claim 1 , further comprising the predictive model predicting a safe mud density window for the target well. 
     
     
         6 . The method of  claim 1 , further comprising the predictive model predicting a pore pressure for the target well. 
     
     
         7 . The method of  claim 1 , in which the historical well data comprises historical drill cuttings data. 
     
     
         8 . The method of  claim 1 , further comprising inputting to the predictive model well data for the target well in real time as the target well is being drilled. 
     
     
         9 . The method of  claim 8 , further comprising the predictive model providing guidance for drilling the target well as the target well is being drilled. 
     
     
         10 . The method of  claim 1 , further comprising producing a correlation model for a relationship between mud density, temperature and mud rheology. 
     
     
         11 . A system for use with a subterranean well drilling operation, the system comprising:
 a predictive model trained to predict at least one historical wellbore event, based on historical well data,   in which the predictive model is configured to predict a probability of a wellbore event occurring in a target well, and   in which the predictive model is configured to provide guidance for drilling the target well.   
     
     
         12 . The system of  claim 11 , in which the historical well data includes drill cuttings data. 
     
     
         13 . The system of  claim 11 , in which the predictive model comprises artificial intelligence. 
     
     
         14 . The system of  claim 11 , in which the guidance comprises a safe mud density window. 
     
     
         15 . The system of  claim 11 , in which the predictive model is further configured to predict the probability of the wellbore event occurring in the target well, based in part on geomechanics principles provided to the predictive model. 
     
     
         16 . The system of  claim 11 , in which the predictive model is further configured to provide the guidance for drilling the target well, based in part on geomechanics principles provided to the predictive model. 
     
     
         17 . The system of  claim 11 , in which the historical well data is recorded for at least one offset well. 
     
     
         18 . The system of  claim 11 , in which the predictive model comprises a correlation model for a relationship between mud density, temperature and mud rheology. 
     
     
         19 . The system of  claim 11 , in which the historical well event comprises at least one of the group consisting of wellbore collapse, wellbore instability and stuck pipe. 
     
     
         20 . The system of  claim 11 , in which the predictive model is configured to predict horizontal stresses in an earth formation of the target well.