Data-driven analytics, predictive modeling and optimization of hydraulic fracturing in shale

摘要

A computer system, comprising: one or more processors; and a memory coupled to the one or more processors, wherein the computer system is programmed with a set of computer-readable instructions configured to implement a method for determining a drill site in a shale, tight gas sands, coal bed methane or other unconventional well field for an oil or gas well and one or more parameter settings therefore, the computer-readable instructions comprising: one or more data mining instructions for data mining of a first part of a set of measurement or objective data parameters from existing oil or gas wells in the well field that, when executed, produce a ranking of each parameter and its respective effect on oil or gas well production from the well field; one or more training instructions that, when executed, produce a model comprising an artificial neural network (ANN) trained with the first part of the set of measurement or objective data parameters and/or the ranking that is useful for producing a group of optimized settings for one or more of the parameters for an estimated maximum output from one or more locations in the well field; and one or more calibration and/or validation instructions that, when executed, calibrate and/or validate the model using a second part of the set of measurement or objective data parameters from existing oil or gas wells in the well field.