A data driven model for the impact of IFT and density variations on CO$_{\mathrm{2}}$ sequestration in porous media

CO$_{\mathrm{2}}$ storage in geological formations is one of the most promising solutions for mitigating the amount of greenhouse gases released into the atmosphere. One of the important issues for CO$_{\mathrm{2}}$ storage in subsurface environments is the sealing efficiency of low-permeable cap-rocks overlying potential CO$_{\mathrm{2}}$ storage reservoirs. A novel model is proposed to find the IFT of the systems (CO$_{\mathrm{2}}$/brine-salt) in a range of temperatures (300-373 K), pressures (50-250 bar), and up to 6 molal salinity applicable to CO$_{\mathrm{2}}$ storage in geological formations through a machine learning-assisted modeling of experimental data. The IFT between mineral surfaces and CO$_{\mathrm{2}}$/brine-salt solutions determines the efficiency of enhanced oil or gas recovery operations as well as our ability to inject and store CO$_{\mathrm{2}}$ in geological formations. Finally, we use the new model to evaluate the effects of formation depth on the actual efficiency of CO$_{\mathrm{2}}$ storage. The results indicate that, in the case of CO$_{\mathrm{2}}$ storage in deep subsurface environments as a global-warming mitigation strategy, CO$_{\mathrm{2}}$ storage capacity are improved with reservoir depth.