Geological CO₂ sequestration (GCS) has been proposed as an effective approach to mitigate carbon emissions in the atmosphere. Uncertainty and sensitivity analysis of the fate of CO₂ dynamics and storage are essential aspects of large-scale reservoir simulations. This work presents a rigorous machine learning-assisted (ML) workflow for the uncertainty and global sensitivity analysis of CO₂ storage prediction in deep saline aquifers. The proposed workflow comprises three main steps: The first step concerns dataset generation, in which we identify the uncertainty parameters impacting CO₂ flow and transport and then determine their corresponding ranges and distributions. The training data samples are generated by combining the Latin Hypercube Sampling (LHS) technique with high-resolution simulations. The second step involves ML model development based on a data-driven ML model, which is generated to map the nonlinear relationship between the input parameters and corresponding output interests from the previous step. We show that using Bayesian optimization significantly accelerates the tuning process of hyper-parameters, which is vastly superior to a traditional trial–error analysis. In the third step, uncertainty and global sensitivity analysis are performed using Monte Carlo simulations applied to the optimized surrogate. This step is performed to explore the time-dependent uncertainty propagation of model outputs. The key uncertainty parameters are then identified by calculating the Sobol indices based on the global sensitivity analysis. The proposed workflow is accurate and efficient and could be readily implemented in field-scale CO₂ sequestration in deep saline aquifers.

This study illuminates the mineral carbonation potential of zeolite minerals. Zeolite minerals are common alteration products of basaltic rocks and are known for their ability to rapidly exchange their interstitial cations with those in aqueous solutions. A series of closed system batch reactor experiments was conducted at 60 °C by combining stilbite, a Ca-bearing zeolite, with 0.1 mol/kg_w aqueous sodium carbonate solutions. The individual batch reactor experiments ran from 2 to 225 days. Scanning electron microscope images of the solids recovered from the experiments reveal the presence of extensive calcite crystals, suggesting rapid and efficient carbonation. The total mass of CO₂ mineralized during the experiments, determined from the direct analysis of the solids by thermogravimetric analysis and organic carbon analysis, equaled more than 5% of that of the original stilbite within a month. This is approximately equal to maximum CO₂ mineralization possible if all of the Ca in the original stilbite was incorporated into calcite. Chemical analysis of reacted stilbite shows that approximately 2 Na atoms were incorporated into stilbite for each Ca atom incorporated into the precipitated calcite. These observations indicate that the carbon removal by stilbite proceeded by the rapid exchange of Na for Ca in its structure. This process results in carbonation rates that are far faster than those achieved by a silicate dissolution-carbonate precipitation mechanism. These results, consequently, compel consideration of targeting subsurface mineral carbonation efforts into zeolite-rich rocks.