Data-driven proxy at hydraulic fracture cluster level: A technique for efficient CO2- enhanced gas recovery and storage assessment in shale reservoir

In this paper, a data-driven approach with pattern recognition algorithms is used to develop a new generation of a shale proxy model at the hydraulic fracture cluster level, as a replica of a reservoir simulation model. For more accurate analysis, instead of commonly used mechanistic models, a history-matched hydraulic fractured Marcellus shale pad with multiple stages/clusters is used as a base case to perform the analysis. The detailed procedure for development of the Data-driven proxy model is explained and the model is validated using blind simulation runs. The developed Data-driven proxy model is capable of accurately reproducing the calculated CO2 injection, CO2/CH4 production profiles, and CO2 breakthrough time from the numerical simulation model, for each cluster/stage and horizontal lateral. Joint use of the deterministic reservoir model with the Data-driven proxy model can serve as a novel screening and optimization tool for the techno-economic evaluation of the CO2-Enhanced Gas Recovery (EGR) and Storage process in shale systems.