Having accurate knowledge on CO₂ solubility in reservoir liquids plays a pivotal role in geoenergy harvest and carbon capture, utilization, and storage (CCUS) applications. Data-driven works leveraging artificial neural networks (ANN) have presented a promising tool for forecasting CO₂ solubility. In this paper, an ANN model was developed based on hundreds of documented data to predict CO₂ solubility in both pure water and saline solutions across a broad spectrum of temperatures, pressures, and salinities in reference to underground formation conditions. Multilayer perceptron (MLP) models were constructed for each system, and their prediction results were rigorously validated against the the literature data. The research results indicate that the ANN model is suitable for predicting the solubility of carbon dioxide under different conditions, with root mean square errors (RMSE) of 0.00108 and 0.00036 for water and brine, and a coefficient of determination (R²) of 0.99424 and 0.99612, which indicates robust prediction capacities. It was observed from the ANN model that the saline water case could not be properly expanded to predict the CO₂ solubility in pure water, underscoring the distinct dissolution mechanisms in polar mixtures. It is expected that this study could provide a valuable reference and offer novel insights to the prediction of CO₂ solubility in complex fluid systems.

CO₂ injection into deep saline aquifer reservoirs is promising for long-term storage of greenhouse gases. To reveal the pore-scale mechanisms underlying CO₂-brine displacement in subsurface formations, computational fluid dynamics simulations were performed in digitally reconstructed homogeneous and fractured porous media. Results showed that the displacement processes in the two types of porous media were governed by fundamentally different mechanisms. In homogeneous media, capillary forces associated with complex pore-throat geometries dominated the displacement behavior. Under low driving forces, the migration of CO₂ was strongly restricted by capillary trapping, resulting in limited removal of brine. As the driving force increased, the injection of CO₂ could overcome local pore-throat resistance and achieve effective displacement of brine. In fractured porous media, fracture structures provided preferential flow paths with lower hydraulic resistance, allowing the breakthrough of CO₂ to occur under relatively low driving forces. However, after the breakthrough, fractures contributed only marginally to additional displacement of brine from the rock matrix, as CO₂ preferentially flowed through the fracture channels. The present work provides quantitative and mechanistic insights into CO₂-brine displacement processes in porous media, offering valuable guidance for the assessment and optimization of geological carbon storage strategies.