A New Methodology for Simulation and Optimization of CO₂Sequestration in a Saline Aquifer Using Artificial Neural Network and Model Predictive Control Approach

Abstract

Carbon dioxide sequestration efforts are the subject of intense research due to growing international concerns over CO 2 emissions critically affecting the global climate change. Extensive studies are being done to determine the extent of the CO 2 injection so that CO 2 storage is secure and environmentally acceptable. In this work, CO 2 injection into a saline aquifer is used to simulate an aquifer in Eclipse-100 using a black oil reservoir simulator whose consequent behavior is predicted by an artificial neural network, being trained via the Levenberg-Marquardt algorithm. A generalized predictive control scheme is accommodated in the proposed design methodology to determine the optimal injection rates during the CO 2 injection process, leading to an ultimate goal of maximized residual trapping or equivalently minimized structural trapping of carbon dioxide. This will eventually maximize the total volume of the injected CO 2 , while diminishing the risk of its leakage to the atmosphere due to a fail in the integrity of the formation cap rock. A set of diverse test scenarios has been organized to demonstrate the capabilities of the proposed methodology to tackle the probable practical considerations.