Hydraulic fracturing framework

Abstract

A method can include receiving data for a well in a field and parameter values for hydraulic fracturing of the well in the field; predicting production data responsive to the hydraulic fracturing of the well using at least a portion of the data and at least a portion of the parameter values as input to a machine learning model, where the machine learning model is trained using historical data for the field; and outputting the predicted production data.

What is claimed is: 
     
         1 . A method comprising:
 receiving data for a well in a field and parameter values for hydraulic fracturing of the well in the field;   predicting production data responsive to the hydraulic fracturing of the well using at least a portion of the data and at least a portion of the parameter values as input to a machine learning model, wherein the machine learning model is trained using historical data for the field; and   outputting the predicted production data.   
     
     
         2 . The method of  claim 1 , further comprising determining one or more of the parameter values using an additional machine learning model. 
     
     
         3 . The method of  claim 2 , wherein the additional machine learning model receives initial parameter values as input. 
     
     
         4 . The method of  claim 2 , wherein the additional machine learning model determines one or more values for one or more fracture design parameters. 
     
     
         5 . The method of  claim 4 , wherein the one or more fracture design parameters comprise fracture length, fracture height, and fracture conductivity. 
     
     
         6 . The method of  claim 1 , further comprising generating one or more optimized parameter values using the output predicted production data. 
     
     
         7 . The method of  claim 6 , wherein the generating comprises implementing an objective function in an iterative optimization loop. 
     
     
         8 . The method of  claim 7 , wherein the iterative optimization loop comprises iteratively predicting production data responsive to updating one or more of the parameter values. 
     
     
         9 . The method of  claim 8 , wherein the updating to the one or more of the parameter values comprises implementing an additional machine learning model. 
     
     
         10 . The method of  claim 9 , wherein the additional machine learning model determines one or more values of one or more fracture design parameters. 
     
     
         11 . The method of  claim 1 , further comprising selecting the well from a plurality of wells. 
     
     
         12 . The method of  claim 11 , wherein the selecting the well comprises generating one or more stimulation recommendations for each of the plurality of wells. 
     
     
         13 . The method of  claim 12 , wherein the one or more stimulation recommendations comprise one or more of a perforation recommendation, a matrix acidizing recommendation, and a hydraulic fracturing recommendation. 
     
     
         14 . The method of  claim 12 , wherein the generating comprises determining one or more of a heterogeneity index, a formation damage index, and a productivity index. 
     
     
         15 . The method of  claim 11 , wherein the selecting the well occurs responsive to generating a hydraulic fracturing recommendation for the well. 
     
     
         16 . The method of  claim 11 , wherein the selecting the well comprises determining that the well is an existing well that is underperforming as to fluid production. 
     
     
         17 . The method of  claim 16 , wherein the existing well is a hydraulically fractured well and wherein the hydraulic fracturing comprises re-fracturing of the hydraulically fracture well. 
     
     
         18 . The method of  claim 1 , wherein the field comprises the well in fluid communication with a conventional reservoir or an unconventional reservoir. 
     
     
         19 . A system comprising:
 a processor;   a memory operatively coupled to the processor; and   processor-executable instructions stored in the memory and executable to instruct the system to:
 receive data for a well in a field and parameter values for hydraulic fracturing of the well in the field; 
 predict production data responsive to the hydraulic fracturing of the well using at least a portion of the data and at least a portion of the parameter values as input to a machine learning model, wherein the machine learning model is trained using historical data for the field; and 
 output the predicted production data. 
   
     
     
         20 . A computer-readable storage medium comprising processor-executable instructions executable by a system to instruct the system to:
 receive data for a well in a field and parameter values for hydraulic fracturing of the well in the field;   predict production data responsive to the hydraulic fracturing of the well using at least a portion of the data and at least a portion of the parameter values as input to a machine learning model, wherein the machine learning model is trained using historical data for the field; and   output the predicted production data.