In the quest to mitigate climate change, the energy sector is constantly seeking innovative solutions to reduce carbon dioxide emissions. One promising avenue is the integration of CO2 enhanced oil recovery (EOR) with carbon capture, utilization, and storage (CCUS) efforts. A recent study led by Milad Asghari from the Institute of Petroleum Engineering at the University of Tehran has introduced a groundbreaking approach to optimize this process, potentially revolutionizing how we think about CO2 injection in oil reservoirs.
The study, published in the Journal of Petroleum Exploration and Production Technology, focuses on the minimum miscibility pressure (MMP), a critical parameter in determining the success of CO2 flooding projects. The MMP is the pressure at which CO2 and oil become miscible, allowing for efficient oil recovery. Accurately estimating the MMP is essential for screening and evaluating the viability of CO2 flooding projects, but traditional models often fall short in precision.
Asghari and his team have developed a novel grey-box machine learning modeling method to bridge this gap. Unlike traditional black-box models, which offer little insight into their decision-making processes, grey-box models combine data-driven approaches with physical principles, providing both accuracy and interpretability. “Our grey-box method not only yields remarkable levels of accuracy but also offers user-friendly equations that can be easily applied in the field,” Asghari explains. This innovation could significantly enhance the efficiency and effectiveness of CO2 EOR projects, making them more attractive to energy companies.
The implications of this research are vast. By improving the accuracy of MMP estimation, energy companies can better assess the potential of CO2 flooding in their reservoirs, leading to more informed investment decisions. This could accelerate the adoption of CO2 EOR, not only boosting oil recovery but also contributing to global efforts to reduce CO2 emissions. “The potential of grey-box machine learning modeling as a valuable tool in the field of CO2 flooding is immense,” Asghari states. “It could pave the way for more precise and efficient CCUS strategies, aligning with the growing demand for sustainable energy solutions.”
As the energy sector continues to evolve, the integration of advanced technologies like grey-box machine learning could shape future developments in CCUS and EOR. By providing a more accurate and user-friendly method for estimating MMP, Asghari’s research could help energy companies optimize their operations, reduce costs, and contribute to a more sustainable future. The study, published in the Journal of Petroleum Exploration and Production Technology, marks a significant step forward in the field, offering a compelling case for the adoption of grey-box modeling in CO2 flooding projects.
