ABSTRACT
This chapter is dedicated to the use and application of big data analytics and data-driven solutions to ease the burden of performing such analyses, and making decision making a practical reality. It is a demonstration of the author's intimate involvement with the use of numerical reservoir simulation to model fluid flow in shale. The chapter introduces a data-driven approach with pattern recognition algorithms to develop a new generation of shale smart proxy models at the hydraulic fracture cluster level, in order to replicate the results of reservoir simulation models. It has introduced shale as a potential geological storage for Carbon dioxide. A series of data-driven CO2-enhanced gas recovery and storage (EGR&S) smart proxy models for shale formation are developed based on the pattern recognition capabilities of artificial intelligence and validated by completely blind simulation runs to reproduce the injection and production profiles for the CO2-EGR&S process.
