Evaluating CO2 hydrate kinetics in multi-layered sediments using experimental and machine learning approach: Applicable to CO2 sequestration

In this study, 13 machine learning (ML) models were employed to predict the phase equilibrium temperatures of the CO2 hydrate in systems with salts and organic inhibitors: Multiple Linear Regression (MLR), Support Vector Regression (SVR), k-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Decision Tree (DT), Random Forest (RF), Extra Trees (ET), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LGBM), Histogram-Based Gradient Boosting (HistGB), and eXtreme Gradient Boosting (XGBoost). A dataset consisting of 1801 experimentally measured equilibrium data points was gathered, which included both pure water systems and systems with thermodynamic inhibitors. After data preprocessing, 1402 data points were selected for ML training and validation. Boosting algorithms generally yielded high predictive accuracy, with the MLP demonstrating notably superior accuracy. The predicted equilibrium temperatures for complex systems containing both salts and organic inhibitors were also compared with those calculated by the widely used CSMGem software. With the exception of SVR, KNN, and DT, all models outperformed CSMGem, in terms of statistical assessment. Specifically, the CatBoost model accurately predicted equilibrium temperatures for most test sets of combinations of salts and organic inhibitors. This study underscores the viability of ML models for predicting the phase equilibria of the CO2 hydrate in the presence of single and mixed thermodynamic inhibitors.

Section: Introductionmentioning

confidence: 99%

Predicting Phase Equilibria of CO₂ Hydrate in Complex Systems Containing Salts and Organic Inhibitors for CO₂ Storage: A Machine Learning Approach

Mok,

Go,

Seo

2024

Section: Introductionmentioning

confidence: 99%

“…One such form is under the seabed, where CO 2 can be stored as a lake with a CO 2 hydrate cap, providing enhanced safety and increased storage capacity by preventing CO 2 leakage and allowing for a larger amount of CO 2 to be sequestered beneath the hydrate cap . Another method involves CO 2 hydrate sediments, where CO 2 is injected into marine sediments, resulting in the formation of CO 2 hydrates, thus leveraging the kinetics and morphology of hydrate formation for sequestration, as illustrated in Figure . Additionally, CO 2 replacement with natural gas hydrates (NGH) presents an environmental advantage, as it can exploit the trapped methane for energy while simultaneously storing CO 2 . , These processes not only store carbon but also stabilize methane hydrate formations, providing an innovative dual benefit of potent greenhouse gas management and energy recovery.…”

Section: Introductionmentioning

confidence: 99%

Comprehensive Review and Perspectives of CO₂ Hydrate Storage in Subseafloor Saline Sediments: Formation, Stability, and Optimization Strategies

Kasala,

Fang,

Wang

et al. 2024

Exploring various strategies for CO 2 hydrate storage in subseafloor saline sediments reveals a promising yet challenging path toward mitigating anthropogenic CO 2 emissions and advancing clean energy development. Research has revealed the efficacy of sediment-specific modifications, including the use of inorganic emulsifiers, L-leucine (an amino acid), and nanoparticle coatings, in enhancing CO 2 hydrate formation stability and storage capacity. These modifications aid in overcoming the challenges posed by the harsh environmental conditions of salinity and sediment heterogeneity, providing increased stability, enhanced CO 2 adsorption efficiency, and reduced induction time. Furthermore, advancements in nanomaterials have introduced nanostructured encapsulation systems capable of confining and stabilizing CO 2 within a solid matrix under fluctuating pressure, temperature, and salinity conditions. Incorporating nanoparticles into polymers and surfactants yields a nanofluid that exhibits increased stability, improved wettability, interfacial tension (IFT) reduction, and elevated CO 2 hydrate storage efficiency, with the synergistic effects of these components playing a critical role. Moreover, innovative thermal and pressure manipulation strategies, alongside the integration of kinetic promoters, have shown significant potential in optimizing CO 2 hydrate formation kinetics and enhancing longterm stability. These strategies involve novel electrical heating systems, pressure management techniques, and chemical additives that collectively contribute to increased hydrate formation rates and gas storage capacities. Despite these promising developments, the field faces several challenges, including optimizing encapsulation materials to match geological characteristics, the long-term stability of CO 2 hydrates under extreme conditions, and scaling laboratory experiments to field applications. Addressing these issues necessitates a multifaceted approach, incorporating empirical data and theoretical insights to design, screen, and formulate effective CO 2 hydrate storage solutions in subseafloor saline sediments.

“…17,18 Therefore, storing CO hydrates in marine sediments is a prospective method of carbon storage. 19,20 It is critical to investigate the kinetics of hydrate formation and storage stability in marine sediments. Many researchers have analyzed the effects of various factors on the hydrate formation in simulated marine sediments.…”

Section: Introductionmentioning

confidence: 99%

Effect of Water and Sand Content on Carbon Dioxide Hydrate Formation in the Clay Minerals

Han,

Feng,

et al. 2024

Carbon storage is an essential approach to mitigating global warming and realizing the negative emissions of greenhouse gases. A practical strategy is to immobilize CO 2 in marine sediments in the form of hydrates. Clay, as one of the most significant components of marine sediments, has a critical impact on CO 2 storage and hydrate formation. In this study, montmorillonite was selected as the clay mineral medium, and the effects of the water content, pressure, and clay content on CO 2 storage were investigated. As the water content increased, the form of the CO 2 storage transformed from clay adsorption to hydrate formation, resulting in a significant increase in the final amount of the CO 2 storage. The activity of the bound water was positively correlated with the distance of water molecules from the clay surface. As the pressure increased from 2.5 to 3.5 MPa, the conversion of inner bound water to hydrate was facilitated, leading to an increase in the final amount of CO 2 storage by 88.4%. Compared to pure clay minerals, the mixed clay−sand medium had an enhanced storage capacity, which increased by approximately 46.9%, attributed to the more available water for hydrate formation. Still, the rate of hydrate formation was slower due to decreased permeability resulting from mudding. The experimental results will help us to understand the pattern of hydrate formation from bound water in clay minerals and provide some theoretical basis for realizing CO 2 storage in clay-bearing marine sediments.