Multi-objective optimization of CO2-enhanced gas recovery and sequestration in edge/bottom water-drive gas reservoirs

In order to improve the field gas recovery (FGR) and CO2 sequestration ratio (CSR) for the edge/bottom-water gas reservoirs, a hybrid framework is designed to combine Long Short-Term Memory (LSTM) with Non-dominated Sorting Genetic Algorithm II (NSGA-II) to obtain the optimal CO2 injection and production scheme at different injection and production rates. In this framework, the Latin hypercube sampling method is used to generate the training and testing samples within a given range of injection and production rates, and the corresponding results are obtained by a calling numerical simulator. The proxy model is obtained by using the samples generated from LSTM training to replace the numerical simulator and improve the simulation efficiency. NSGA-II is utilized to determine the Pareto front of the optimal outcomes to maximize FGR and CSR. The robustness of the framework is verified with a typical edge/bottom water-drive gas reservoir. CO2 sequestration process in this gas reservoir after 100 years is simulated based on the optimal solution. The results show that the R2 of the LSTM proxy model for FGR and CSR prediction is greater than 0.99, which indicates that it can replace the numerical simulator accurately. Compared with the basic scheme without optimization, FGR is increased by 6.09% and CSR is increased by 3.91%. Under the optimal scheme, the CO2 distribution for long-period storage is predicted, and the results show CO2 will eventually migrate to the bottom of the reservoir under the influence of gravity, which is contrary to CO2 sequestration in oil reservoirs. It can provide theoretical guidance for CO2 injection for enhanced gas recovery and sequestration in edge/bottom water-drive gas reservoirs.