Journal
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
Volume 76, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.jngse.2020.103208
Keywords
Artificial intelligence; CO2 sequestration; Geological uncertainties; Robust optimization; Trapping mechanism; WAG process; Artificial neural network; CO2 storage
Categories
Funding
- Japan International Cooperation Agency (JICA)
Ask authors/readers for more resources
This study presents a robust optimization workflow to determine the optimal water alternating gas (WAG) process for CO2 sequestration in a heterogeneous fluvial sandstone reservoir. As depicted in this study, WAG injection could enhance CO2 residual and solubility trapping based on an integrated modeling workflow. First, continuous CO2 injection and WAG were compared to demonstrate the efficiency of the WAG process for CO2 trapping enhancement. To achieve this while highlighting the impact of reservoir heterogeneity, 200 geological realizations were generated considering a wide range of plausible geological conditions. The ranking of these realizations was performed by quantifying the CO2 cumulative injection (P10, P50, and P90 realizations) that represent the overall geological uncertainties. Then, an innovative robust workflow was used Artificial Intelligence optimizer to determine the optimal solution for CO2 trapping. For comparison, a nominal optimization workflow of P50 realization was also conducted. The proposed robust optimization workflow resulted in higher CO2 trapping than the nominal optimization workflow. Thus, this study demonstrates a fast and reliable workflow that can accurately represent for optimization the cycle length injection in the WAG process under geological uncertainties.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available