Storage In Deep Saline Aquifers Research Articles

Estimation of CO2-Brine Interfacial Tension Based on an Advanced Intelligent Algorithm Model: Application for Carbon Saline Aquifer Sequestration.

The emission reduction of the main greenhouse gas, CO2, can be achieved via carbon capture, utilization, and storage (CCUS) technology. Geological carbon storage (GCS) projects, especially CO2 storage in deep saline aquifers, are the most promising methods for meeting the net zero emission goal. The safety and efficiency of CO2 saline aquifer storage are primarily controlled by structural and capillary trapping, which are significantly influenced by the interactions between fluid and solid phases in terms of the interfacial tension (IFT) between the injected CO2 and brine at the reservoir site. In this study, a model based on the random forest (RF) model and the Bayesian optimization (BO) algorithm was developed to estimate the IFT between the pure and impure gas-brine binary systems for application to CO2 saline aquifer sequestration. Then three heuristic algorithms were applied to validate the accuracy and efficiency of the established model. The results of this study indicate that among the four mixed models, the Bayesian optimized random forest model fits the experimental data with the smallest root-mean-square error (RMSE = 1.7705) and mean absolute percentage error (MAPE = 2.0687%) and a high coefficient of determination (R2 = 0.9729). Then the IFT values predicted via this model were used as an input parameter to estimate the CO2 sequestration capacity of saline aquifers at different depths in the Tarim Basin of Xinjiang, China. The burial depth had a limited influence on the CO2 storage capacity.

CO2 storage in saline aquifers: A simulation on quantifying the impact of permeability heterogeneity

As one promising technology to mitigate CO2 emission, CO2 capture utilization and storage (CCUS) plays a crucial role in achieving carbon neutrality. The deep saline aquifer is a prime candidate for CO2 geological storage. The subsurface flow and effectiveness of CO2 storage in deep saline aquifer are highly related to the permeability heterogeneity of formations, which needs in-depth study. To bridge the gap, this study focused on quantifying the impact of permeability heterogeneity on the CO2 flow patterns, the well injectivity and the storage efficiency, which aims to enhance the understanding of CO2 storage characteristics in deep saline aquifers. The heterogeneous saline aquifer model was built by using the Sequential Gaussian Simulation (SGSIM) method. A novel classification template was proposed with the CO2 flow patterns classified as “Dispersive”, “Sweeping”, “Fingering”, and “Channeling” for CO2 storage in deep saline aquifers according to the geostatistical parameters (including dimensionless correlation lengths, first and second spatial moment, and Dykstra-Parsons coefficient). For the well injectivity, the results showed that high injectivity occurred when both horizontal and vertical correlation lengths were high or at a favourable connectivity of permeability in the horizontal and vertical directions. In addition, CO2 storage efficiency is higher when both dimensionless horizontal and vertical correlation lengths are in the range of 0.1–0.2. This is because frequent changes between high and low permeability regions led to frequent mutual displacement of water and CO2, resulting in higher residual trapping and slow CO2 front. Therefore, the dimensionless correlation lengths and breakthrough time should be considered simultaneously to achieve safer trapping and maximize the CO2 storage capacity. The findings of this work provide insights into the subsurface flow of CO2 storage in deep saline aquifers with permeability heterogeneity.

Geomechanical risk assessment for CO2 storage in deep saline aquifers

We study CO2 injection into a saline aquifer intersected by a tectonic fault using a coupled modeling approach to evaluate potential geomechanical risks. The simulation approach integrates the reservoir and mechanical simulators through a data transfer algorithm. MUFITS simulates non-isothermal multiphase flow in the reservoir, while FLAC3D calculates its mechanical equilibrium state. We accurately describe the tectonic fault, which consists of damage and core zones, and derive novel analytical closure relations governing the permeability alteration in the fault zone. We estimate the permeability of the activated fracture network in the damage zone and calculate the permeability of the main crack in the fault core, which opens on asperities due to slip. The coupled model is applied to simulate CO2 injection into synthetic and realistic reservoirs. In the synthetic reservoir model, we examine the impact of formation depth and initial tectonic stresses on geomechanical risks. Pronounced tectonic stresses lead to inelastic deformations in the fault zone. Regardless of the magnitude of tectonic stress, slip along the fault plane occurs, and the main crack in the fault core opens on asperities, causing CO2 leakage out of the storage aquifer. In the realistic reservoir model, we demonstrate that sufficiently high bottomhole pressure induces plastic deformations in the near-wellbore zone, interpreted as rock fracturing, without slippage along the fault plane. We perform a sensitivity analysis of the coupled model, varying the mechanical and flow properties of the storage layers and fault zone to assess fault stability and associated geomechanical risks.

Brine Salinity: A Deciding Factor for Carbondioxide Dissolution and Trapping during Geological Sequestration

Adequate geological storage of carbondioxide in saline aquifers is a function of several factors that requires understanding and examination. Previous works have argue that solubility of carbondioxide in brine decreases as the salinity of the brine increases, but it is unclear in the literature the impact of salinity on carbondioxide (CO2) trapping during sequestration. This work adopt a simulation based approach to determine CO2 dissolution and trapping at different salinities. A dataset was written and validated with CMG’s greenhouse gases simulator and the thermodynamics properties calculation carried out with Peng-Robinson equation of state. Four sensitivity analyses was conducted with brines of no salinity (pure water), salinity of 100000ppm, 200000ppm and 300000ppm and model outputs compared for CO2 sequestration. The result shows that CO2 solubilised in water with zero level salinity, and a lower gas cap size was formed at the top of the structure. Later, gas cap size increases as the salinity level increases at the top of the structure. Also, the moles soluble in water decreases as the salinity level increases with the least moles for zero water salinity. Alternatively to the moles solubilised, the number of moles of CO2 trapped increases with the salinity level. CO2 storage in deep saline aquifers is the best storage techniques but its injection into aquifer of high salinity reduced its solubility.

Enhancing carbon sequestration: Innovative models for wettability dynamics in CO2-brine-mineral systems

This study investigates the application of machine learning techniques—specifically convolutional neural networks, multilayer perceptrons and cascaded forward neural networks —to understand the wettability of the CO2/brine/rock system, a critical factor in carbon dioxide (CO2) capture, utilization, and storage in deep saline aquifers. Understanding wettability is essential for improving the efficacy of CO2 storage. The study incorporates variables such as salinity, mineral types, measurement methods, pressure, and temperature into the machine learning models. Using a dataset of 876 samples from existing literature, the proposed models were trained and optimized using the Adam optimizer, Levenberg-Marquardt algorithm, and particle swarm optimization respectively.The performance of these models was evaluated through plot analysis, statistical indicators, and the Taylor diagram, demonstrating a high level of accuracy compared to experimental data. The specifically convolutional neural networks model showed exceptional accuracy in predicting CO2 wettability in brine, with a root mean square error of 0.9612 and coefficient of determination value of 0.9982. The minimal presence of outliers in the specifically convolutional neural networks model further confirms its robustness.This research highlights the effectiveness of deep learning in modeling complex wettability behaviors in CO2-brine-mineral systems, offering substantial insights for enhancing carbon dioxide (CO2) capture, utilization, and storage strategies. The novelty of this work lies in its comprehensive integration of multiple variables and the use of advanced machine learning optimization techniques, going beyond previous efforts by achieving higher predictive accuracy and providing a more detailed understanding of wettability dynamics.

Hydrogen Storage in Deep Saline Aquifers: Non-Recoverable Cushion Gas after Storage

Underground hydrogen storage facilities require cushion gas to operate, which is an expensive one-time investment. Only some of this gas is recoverable after the end of UHS operation. A significant percentage of the hydrogen will remain in underground storage as non-recoverable cushion gas. Efforts must be made to reduce it. This article presents the results of modeling the cushion gas withdrawal after the end of cyclical storage operation. It was found that the amount of non-recoverable cushion gas is fundamentally influenced by the duration of the initial hydrogen filling period, the hydrogen flow rate, and the timing of the upconing occurrence. Upconing is one of the main technical barriers to hydrogen storage in deep saline aquifers. The ratio of non-recoverable cushion gas to cushion gas (NRCG/CG) decreases with an increasing amount of cushion gas. The highest ratio, 0.63, was obtained in the shortest 2-year initial filling period. The lowest ratio, 0.35, was obtained when utilizing the longest initial filling period of 4 years and employing the largest amount of cushion gas. The presented cases of cushion gas recovery can help investors decide which storage option is the most advantageous based on the criteria that are important to them.

Toward Predicting Interfacial Tension of Impure and Pure CO2-Brine Systems Using Robust Correlative Approaches.

In the context of global climate change, significant attention is being directed toward renewable energy and the pivotal role of carbon capture and storage (CCS) technologies. These innovations involve secure CO2 storage in deep saline aquifers through structural and capillary processes, with the interfacial tension (IFT) of the CO2-brine system influencing the storage capacity of formations. In this study, an extensive data set of 2811 experimental data points was compiled to model the IFT of impure and pure CO2-brine systems. Three white-box machine learning (ML) methods, namely, genetic programming (GP), gene expression programming (GEP), and group method of data handling (GMDH) were employed to establish accurate mathematical correlations. Notably, the study utilized two distinct modeling approaches: one focused on impurity compositions and the other incorporating a pseudocritical temperature variable (Tcm) offering a versatile predictive tool suitable for various gas mixtures. Among the correlation methods explored, GMDH, employing five inputs, exhibited exceptional accuracy and reliability across all metrics. Its mean absolute percentage error (MAPE) values for testing, training, and complete data sets stood at 7.63, 7.31, and 7.38%, respectively. In the case of six-input models, the GEP correlation displayed the highest precision, with MAPE values of 9.30, 8.06, and 8.31% for the testing, training, and total data sets, respectively. The sensitivity and trend analyses revealed that pressure exerted the most significant impact on the IFT of CO2-brine, showcasing an adverse effect. Moreover, an impurity possessing a critical temperature below that of CO2 resulted in an elevated IFT. Consequently, this relationship leads to higher impurity concentrations aligning with lower Tcm values and subsequently elevated IFT. Also, monovalent and divalent cation molalities exhibited a growing influence on the IFT, with divalent cations exerting approximately double the influence of monovalent cations. Finally, the Leverage approach confirmed both the reliability of the experimental data and the robust statistical validity of the best correlations established in this study.

Numerical simulation study of CO2 storage capacity in Deep Saline aquifers

The storage of supercritical CO2 in deep saline aquifers is essential for reducing carbon emissions, and the selection of an appropriate reservoir is a primary consideration for carbon sequestration. To investigate the impact of reservoir physical properties on the CO2 storage capacity of saline aquifers, this study establishes a numerical simulation model of CO2 storage in deep saline aquifers and utilizes the MRST toolbox to solve it by the finite volume method. The research thoroughly analyzes the influence of reservoir physical properties on the CO2 migration process and CO2 storage capacity of the saline aquifer layer. The results show that prolonged CO2 injection involves a process of initially suppressing pressure and subsequently slowly diffusing it to the surroundings. Furthermore, the physical properties of the reservoir and the reservoir pressure significantly influence CO2 burial in deep saline aquifers. Higher reservoir permeability and deeper burial depth result in enhanced CO2 storage and faster CO2 plume migration. However, the porosity and temperature of the reservoir have a negligible impact on CO2 storage. Our research work provides a precise understanding of selecting suitable layers for CO2 storage in deep saline aquifers, offering strong support for early predictions of carbon capture, utilization, and storage (CCUS).

Minireview on CO2 Storage in Deep Saline Aquifers: Methods, Opportunities, Challenges, and Perspectives

Minireview on CO₂ Storage in Deep Saline Aquifers: Methods, Opportunities, Challenges, and Perspectives

Induced Seismicity Hazard Assessment for a Potential CO2 Storage Site in the Southern San Joaquin Basin, CA

California’s Central Valley offers vast opportunities for CO2 storage in deep saline aquifers. We conducted an induced seismicity hazard assessment for a potential injection site in the southern San Joaquin Basin for 18 years of injection at 0.68 MtCO2/yr and 100 years of monitoring. We mapped stress, faults, and seismicity in a 30 km radius around the site to build a geomechanical model and resolve the stresses on major faults. From a 3D hydromechanical simulation of the CO2 plume, we calculated the change in pressure over time on these faults and determined the conditions for safe injection. Lacking any subsurface imaging, we also conducted a probabilistic fault slip analysis using numerous random distributions of faults and a range of geomechanical parameters. Our results show that the change in probability of fault slip can be minimized by controlling the size, migration, and magnitude of the pressure plume. We also constructed a seismic catalog for the last 20 years around the site and characterized the natural patterns of seismicity. We use these results to establish criteria for evaluating potential-induced events during the storage period and to develop a traffic light response system. This study represents a first-order procedure to evaluate the seismic hazards presented by CO2 storage and incorporate uncertainties in hydrological and geomechanical parameters.

Numerical sensitivity analysis of CO2 mineralization trapping mechanisms in a deep saline aquifer

There is a growing interest in geo-sequestration of CO2 for its safe disposal given the emergency of global greenhouse gas emissions reduction. Depleted oil and gas fields and deep saline aquifers are the most promising CO2 storage locations. Deep saline aquifers have been regarded preferable due to their widespread and great storage capacity. However, there exists a notable research gap regarding the understanding of CO2 geochemical reactivity with in-situ minerals, specifically in deep saline aquifers. Hence, this study focuses on the mineralization trapping mechanisms of CO2 by simulating the sequestration of at least 48 million tons of CO2 over a five-year period in a saline aquifer. The effectiveness of CO2 mineralization trapping for the siliciclastic aquifer was analyzed and characterized in relation to injection period, pressure, temperature, and salinity. The ability of the aquifer to store significant amounts of injected CO2 for a duration of 1000 years was studied using a numerical simulator. Our study also examines geochemical-induced changes, such as pH and porosity, resulting from mineralization. The results reveal that longer injection periods enhance the efficiency of CO2 mineralization trapping, primarily due to the increased availability of CO2 in the reservoir. Moreover, our findings provide valuable insights into the optimal mineralization temperatures for the simulated minerals, determining their dissolution or precipitation tendencies. Notably, calcite and dolomite exhibit higher mineralization efficiency at medium and lower temperatures, while minerals like illite, kaolinite, K-feldspar, and quartz are more favorably reactive at higher temperatures. Although porosity and pH exhibited minimal variations, they were sufficient to indicate the dynamics of mineral reactivity and mineralization trapping efficiency. By addressing these research gaps and presenting our novel findings, this study significantly contributes to the understanding of CO2 storage in deep saline aquifers and offers valuable insights for optimizing CO2 mineralization processes.

Numerical Comparison of Hydrogen and CO2 Storage in Deep Saline Aquifers from Pore Scale to Field Scale

Numerical Comparison of Hydrogen and CO2 Storage in Deep Saline Aquifers from Pore Scale to Field Scale

Pore‐Scale Modeling of Coupled CO2 Flow and Dissolution in 3D Porous Media for Geological Carbon Storage

AbstractDissolution trapping is one of the crucial trapping mechanisms for geological carbon storage in deep saline aquifers. The injected supercritical CO2 (scCO2) flow and dissolution processes are coupled and interact with each other. Therefore, we performed direct numerical simulations in three‐dimensional micro‐CT images of sandstones using the volume of fluid and continuous species transfer method. We investigated the coupled scCO2 flow and dissolution processes at pore‐scale under different rock structures, capillary numbers, and rock wettability conditions. The dynamic evolution of the scCO2/brine phase distribution and scCO2 concentration distribution occurring during the injection period were presented and analyzed. Complicated coupling mechanisms between scCO2‐brine two‐phase flow and interphase mass transfer were also revealed. Our results showed that the scCO2 dissolution was highly dependent on the local distribution of scCO2 clusters. The rock with relatively high porosity and permeability would have more capacity for scCO2 injection resulting in a faster and greater dissolution of scCO2 in brine. The effect of capillary number on the scCO2 dissolution process was related to the range of capillary number. The effective upscaled (macro‐scale) mass transfer coefficient (kA) during scCO2 dissolution was evaluated, and the power‐law relationship between kA and Péclet number was obtained. Rock wettability was found to be another factor controlling the scCO2 dissolution process by affecting the scCO2‐brine interfacial area. Our pore‐scale study provides a deep understanding of the scCO2 dissolution trapping mechanism, which is important to enhance the prediction of sequestration risk and improve sequestration efficiency.

Migration characteristics and local capillary trapping mechanism after the CO2 leakage out of saline aquifers

CO2 may leak from the wellbore, cross-section of faults, fractures, and pore space due to geological tectonic activity or human-induced activity during the CO2 geological storage in deep saline aquifers. To evaluate the CO2 leakage risk and select safe saline aquifers, it is necessary and crucial to predict the CO2 migration characteristics and trapping mechanism after its leakage. Although some previous studies have shown that heterogeneous capillary pressure can change CO2 migration path, its impact on the migration and storage after CO2 leakage is still unclear. Therefore, a simulation model of CO2 leakage and migration in saline aquifers is established by adopting stochastic modeling in geology and two-phase seepage modeling in the fluid. Based on the model, the influence of capillary pressure heterogeneity and caprock factors (thickness and leakage area) on the leaked CO2 migration, distribution, and trapping is analyzed quantitatively. The research result shows that heterogeneous capillary pressure in the saline aquifers can effectively trap the leaked CO2 and enlarge the lateral swept volume of leaked CO2. With the increase of capillary pressure and its heterogeneity, the upward migration of CO2 slows down but the local capillary trapping increases. Both of these can weaken the risk of CO2 leakage to the surface. Under the local capillary trapping above and below the caprock, the increasing of caprock thickness and leakage area have little effect on CO2 leakage amount, but may increase the local capillary trapping and make the formation safer. Therefore, priority should be given to selecting saline aquifers with thicker caprock to reduce the potential risk of CO2 leakage. In order to ensure the safety of CO2 storage, a saline aquifer with strong capillary pressure heterogeneity and good trapping performance should be selected.

Simulation Study of sc-CO2 Based Silylation for Decreasing Severity of Water Blockage and Salt Precipitation during Geological CO2 Storage in Deep Saline Aquifers

Deep saline aquifers are often favorable for underground CO2 sequestration due to their large capacity and relatively low likelihood for resource conflicts. However, many possible issues can arise during CO2 injection. Often these aquifers have a significant salinity level (as these often present minimal resource conflict issues) and as such salt precipitation near the injection wellbore can be problematic. Furthermore, when water blockage occurs, salt precipitation can be exacerbated since large amounts of water remain near the wellbore. Altering the rock wettability towards less water-wet can alleviate water blockage and in turn reduce the likelihood or severity of salt precipitation. Previous lab experiments have shown that supercritical CO2 (sc-CO2)-based silylation can effectively functionalize rock surfaces with hydrophobic silanes. In this study, numerical models were constructed to evaluate the combined effects of multi-phase fluid flow, water evaporation and salt precipitation assuming a change in wettability (thus impacting the relative permeability characteristics of the reservoir) resulting from the silylation process. The aim of this study is to evaluate the efficacy of this chemical treatment to address near wellbore salt precipitation induced by CO2 injection. According to the simulation results, a decrease in injectivity due to salt precipitation is more significant when water blockage is also present. Injectivity is deteriorated prominently in high salinity reservoirs with water blockage since evaporation into the injected CO2 phase will cause significant salt precipitation. In a representative formation, the injectivity decline is worse (up to 68.6% relative injectivity change (RIC)) when both salt precipitation and water blockage are considered since the latter provides more trapped brine inducing more salt accumulation around the wellbore. With hydrophobic silylation, the combined effects of salt precipitation and water blockage on RIC are decreased on an absolute basis by up to 7%. Depending on techno-economic considerations, this method is encouraged to be implemented as early as possible during a CO2 injection program to minimize salt accumulation from the outset.

Numerical study of the efficiency of underground hydrogen storage in deep saline aquifers, rock springs uplift, Wyoming

Underground hydrogen storage (UHS) is able to store a large amount of energy with efficiency, thus meeting the high demand for energy in winter. This study aims at investigating the feasibility and efficiency of UHS in the Nugget Sandstone, Rock Springs Uplift, Wyoming. The representative geological model is first constructed with the control of well logs and seismic data. Then the multiphase flow functions are well coupled into the subsurface reservoir model. Following that, based on the uncertainty of reservoir parameters, gas source accessibility, and production cost, the effects of key parameters on H2 fate within the reservoir and H2 recovery efficiency are researched. Simulation outcomes reveal that H2 dissolution into formation brine gives rise to a lower amount of trapped H2 within the reservoir but the recovery ratio is reduced by the H2 dissolution at the end. Relative permeability hysteresis can not only relieve the H2 vertical migration, but also give a wider H2 radial distribution. As the cycle proceeds, relative permeability hysteresis results in the notable enhancement in the trapped H2, leading to a reduction of the final recovery ratio from 0.86 to 0.76 when the residual gas saturation, Sgmax, ranges from 0.2 to 0.4. A slower cushion gas (CG) injection rate gives rise to a smaller final trapped H2, which accordingly results in an increase of recovery ratio. Further, the final recovery ratio changes from 0.835 to 0.846 due to an increase in working gas components from H2:CH4 = 1:1 to H2:CH4 = 3:1. The insights obtained in this study shed a light on accelerating the achievements of decarbonisation goals through the commercial-scale energy conversion and transition from conventional fossil energy and renewable energy to hydrogen.

Efficient simulation of CO2 migration dynamics in deep saline aquifers using a multi-task deep learning technique with consistency

CO2 sequestration and storage in deep saline aquifers is a promising technology for mitigating the excessive concentration of the greenhouse gas in the atmosphere. However, accurately predicting the migration of CO2 plumes requires complex multi-physics-based numerical simulation approaches, which are prohibitively expensive due to highly nonlinear coupled governing equations and uncertainties in heterogeneous spatial parameter distributions. To address this challenge, we developed an end-to-end deep learning workflow employing encoder–decoder architectures with residual network (ResNet) to efficiently predicts the spatial–temporal evolution of the solution CO2-brine ratio (Rs) and gas saturation (Sg) – the two essential tasks for quantifying the amount of trapped CO2 – given heterogeneous permeability fields as input. Specifically, we introduce a general multi-task learning with consistency (MTLC) framework to simultaneously predict Rs and Sg. The MTLC model leverages related tasks with less computational expensive labeled datasets to improve generalization ability. In our study, predictions for multiple tasks from the same permeability realization are not independent but expected to be consistent, as the proposed framework utilizes data-driven cross-task consistency constraints to augment learning of related tasks. Our deep learning model is trained based on physical trapping mechanisms, which play a dominant role in the CO2 migration process. The results demonstrate that the MTLC model with joint learning yields more accurate predictions and improved generalization for predicting CO2 migration in several test cases. Furthermore, our workflow is 105 times faster than a high-fidelity physics-based numerical simulator, making it a viable alternative for field-scale applications.

Selecting Geological Formations for CO2 Storage: A Comparative Rating System

Underground storage of carbon dioxide (CO2) in geological formations plays a vital role in carbon capture and storage (CCS) technology. It involves capturing CO2 emissions from industrial processes and power generation and storing them underground, thereby reducing greenhouse gas emissions and curbing the impact of climate change. This review paper features a comparative analysis of CO2 storage in deep saline aquifers, depleted reservoirs, coal seams, basaltic formations and clastic formations. The comparison has been drawn based upon seven factors carefully selected from the literature, i.e., safety, storage capacity, injection rates, efficiency, residual trapping, containment and integrity and potential to improve, and all of these factors have been rated from low (1) to high (5) based upon their individual traits. Based upon these factors, an overall M.H. rating system has been developed to categorize geological formations for CO2 storage and it is observed that deep water aquifers and basaltic formations are the most effective options for CO2 storage. Lastly, a detailed way forward has been suggested, which can help researchers and policymakers to find more viable ways to enhance the efficiency of CO2 storage in various geological formations.

Geological Conditions and Suitability Evaluation for CO2 Geological Storage in Deep Saline Aquifers of the Beibu Gulf Basin (South China)

The geological storage of carbon dioxide (CO2) is the most suitable option to achieve a large-scale and low-cost CO2 emissions worldwide, but the selection of favorable areas for the geological storage is the main issue. In this study, evaluation indicators were selected considering four aspects, namely geological conditions, storage potential, hydrogeological conditions, and engineering conditions, based on drilling, geophysical, and geochemical data from the Beibu Gulf Basin. The analytical hierarchy process and the fuzzy comprehensive evaluation method were used to evaluate the suitability of this basin for geological storage of CO2. The results suggested that: (1) the Beibu Gulf Basin is suitable for CO2 geological storage, and the evaluation grade is the highest rating level; (2) considering the techno-economic feasibility, it is necessary to select the target area for CO2 geological storage with suitable burial depth, superior reservoir conditions, proximity to the CO2 collection device, and a high degree of exploration.

Uncertainty Analysis of CO2 Storage in Deep Saline Aquifers Using Machine Learning and Bayesian Optimization

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.