Uncertainty quantification for CO2 storage during intermittent CO2-EOR in oil reservoirs

• Published in: International journal of coal geology 2023-02, Vol.266, p.104177, Article 104177
• Main Authors: Rezk, Mohamed Gamal, Ibrahim, Ahmed Farid, Adebayo, Abdulrauf R.
• Format: Article
• Language: English
• Subjects: CO2 sequestration; Enhanced oil recovery; Intermittent CO2 assisted gravity drainage; Machine Learning; Response surface methodology; Uncertainty quantification
• ISSN: 0166-5162; 1872-7840
• DOI: 10.1016/j.coal.2022.104177

CO2 enhanced oil recovery (CO2-EOR) process is considered the most feasible option for a secure storage of CO2 in underground formations. However, predicting amounts of CO2 stored and the oil recovered is associated with high risks due to data uncertainty. Sources of uncertainty lie in the challenges of accurately characterizing reservoir properties. Hence, the main objective of this study is to quantify the uncertainty of CO2 storage and oil recovery during intermittent CO2-assisted gravity drainage (CO2-GAGD) EOR process with a focus on key uncertain parameters including reservoir properties (permeability heterogeneity, porosity, and compressibility); fluid properties (CO2 diffusion coefficient and Henry's constant); and rock-fluid properties (gas-oil relative permeability data). Additionally, we aim to generate a rapid tool that reduces the computational expenses of the compositional reservoir simulation process by employing artificial neural network (ANN) as a machine learning (ML) tool. ANN was applied to generate predictive models that accurately predicted oil recovery and gas storage during the intermittent CO2-GAGD process. A total of 173 numerical samples were simulated and the objective functions were obtained. From the defined ranges of input variables and simulation results, cumulative distribution functions (CDFs) were obtained and uncertainty bounds, i.e., P10, P50, and P90, were estimated. Additionally, the generated ANN model showed excellent predictions of the objective functions with high correlation coefficients, higher than 0.98 in most of the cases, and with an absolute average percentage error (AAPE) range from 2.6 to 9%. Finally, the results of sensitivity analysis, conducted using the developed ML models with generating 10,000 realizations from the input and output parameters, showed the most influential input parameters on the performance of the CO2 storage and oil recovery factor. Reservoir porosity was found to have a significant impact on oil recovery and CO2 storage. A response surface analysis showed that the main independent input parameters contributing to the total uncertainty of oil recovery were horizontal permeability, oil relative permeability, and formation porosity. This study highlights the significant impact of uncertainties of input parameters on simulating the performance of CO2 storage and oil recovery in underground reservoirs.