Maximizing Recovery in CO2-EOR by a Holistic, Bottom-up, and Multi-scale Experimental and Simulation Approach Involving Machine Learning Optimization

Principal Investigator
Waleed Alameri
Department
Petroleum Engineering
Focus Area
Hydrocarbon Exploration & Production
Maximizing Recovery in CO2-EOR by a Holistic, Bottom-up, and Multi-scale Experimental and Simulation Approach Involving  Machine Learning Optimization

The proposed project aims to develop a holistic, yet focused, experimental and simulation optimization approach involving novel nanoscale experimental tools coupled to artificial intelligence (AI) in order to provide a solid pathway for maximizing efficiency and recovery upon CO2-based EOR.

The project involves additives development and evaluation, core-flooding experiments, rheology studies and CO2-additive-oil flow evaluation, studies on rock physicochemical characteristics, pore analysis, and rockā€“CO2-additives interactions, in-situ neutron scattering experiments, all integrated into the development of Machine Learning (ML) simulations and optimization algorithms.

With this appoach, we target bottom-up optimization, provided by the proposed toolset, which is applied for the first time in EOR. CO2-EOR will be the focal case study, but the technology to be developed will have the potential to be expanded and applied to other EOR technologies of interest, such as polymer-EOR.

Maximizing Recovery in CO2-EOR by a Holistic, Bottom-up, and Multi-scale Experimental and Simulation Approach Involving  Machine Learning Optimization