A reliable model to predict the methane-hydrate equilibrium: An updated database and machine learning approach

Hosseini, Mostafa; Leonenko, Yuri

doi:10.1016/j.rser.2022.113103

Cited by 9 publications

(8 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The chemical formula for MH is CH 4 ·5.75H 2 O or 8CH 4 ·46H 2 O. It is an icelike solid compound with plenty of CH 4 formed after CH 4 is caged within water molecules that are stable at low temperatures and high pressure in ocean floor sediments at water depths greater than 500 m and beneath Arctic permafrost. − Several different names also refer to methane hydrate. They include hydromethane, methane clathrate, fire ice, methane ice, natural gas hydrate, and gas hydrate.…”

Section: Theorymentioning

confidence: 99%

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO₂–CH₄ Exchange: Experiments, Simulations, and Pilot Test Applications

et al. 2023

View full text Add to dashboard Cite

Many researchers have investigated the potential of methane hydrate reservoirs (MHRs) for carbon dioxide (CO2) sequestration and methane (CH4) production through the CO2–CH4 replacement method. This technique is not yet commercially implemented due to various limitations, especially economic reasons. This study investigated recent advancements in MHRs potentiality for CO2 sequestration through CO2 or mixed gas exchange injection while recovering CH4. From the experiments, modeling, and simulations, and one pilot test conducted, it was found that there is a great potentiality of sequestrating CO2 in MHRs while recovering CH4. In addition, it was revealed that to produce more CH4, the nitrogen/hydrogen (N2/H2) mole fraction in the injector gas stream should be more significant than that in CO2, while to sequestrate more CO2, the CO2 mole fraction in the injector gas stream should be greater than the N2/H2 mole fraction. The CO2–mixture gases mole fraction ratio recommended from one successful pilot test conducted was 23:77 (CO2/N2), which revealed that approximately 60% of injected CO2 was sequestrated with 855 × 103 standard cubic feet of CH4 produced. The challenges identified in this review will urge researchers to explore suitable technologies to conduct more pilot tests and pave the way toward entire field operations on CO2 sequestration in MHRs toward decarbonization.

show abstract

Section: Theorymentioning

confidence: 99%

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO₂–CH₄ Exchange: Experiments, Simulations, and Pilot Test Applications

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Recent advancements in machine learning (ML) offer a promising alternative for predicting hydrate phase equilibria, as ML is inherently data-driven and can model complex relationships within large datasets. 14 Unlike traditional methods, ML algorithms continuously refine their predictive capabilities through autonomous learning from data. This selflearning is facilitated by advancements in high-speed computational techniques and the availability of user-friendly algorithm design platforms.…”

Section: ■ Introductionmentioning

confidence: 99%

“…17 Since the introduction of artificial intelligence applications in hydrate equilibrium prediction in the late 20th century, various types of ML models, such as k-Nearest Neighbors (KNN), Decision Tree (DT), and Support Vector Regression (SVR), have been utilized. 14,17,18 More recently, advanced approaches have emerged that incorporate variations of existing models, such as Least Squares Support Vector Machines (LSSVM), and ensemble methods, including Random Forest (RF) and Extra Trees (ET). 19 Evolutionary algorithms such as Gene Expression Programming (GEP) have also been employed to predict equilibria of mixed gas hydrates, and neural network-based algorithms, including Multi-Layer Perceptron (MLP) and Adaptive Neuro-Fuzzy Inference System (ANFIS), have enriched the array of predictive tools.…”

Section: ■ Introductionmentioning

confidence: 99%

“…Conventional experimental measurements of hydrate phase equilibria are generally time-intensive, prompting extensive research into thermodynamic modeling and correlation-based predictive methods. Recent advancements in machine learning (ML) offer a promising alternative for predicting hydrate phase equilibria, as ML is inherently data-driven and can model complex relationships within large datasets . Unlike traditional methods, ML algorithms continuously refine their predictive capabilities through autonomous learning from data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Energy Fuels

View full text Add to dashboard Cite

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.

show abstract

“…Apart from these thermodynamic approaches, numerous correlations based on system composition exist to describe the HLVE in the presence of salts. − Others have employed machine learning to estimate the same HLVE. − However, both of these approaches rely on the availability of uniformly distributed experimental data to negate any bias toward a particular system composition.…”

Section: Introductionmentioning

confidence: 99%

Formulating Noncovalent Interactions for Gas Hydrates with Electrolytes: A New Approach of Stability Analysis

Dongre

Jana

2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Understanding of gas hydrate stability is crucial for the prediction of hydrate equilibrium pressures in the presence of electrolytes. In this contribution, a new theoretical framework is conceptualized to describe the hydrate phase precisely. For this, a noncovalent interaction analysis is proposed to be performed on a unit hydrate lattice composed of pure and mixed guests in the vicinity of salts at the B3LYP-D3+def2-SVPD level of theory. It is seen that the guests affect the steric and hydrogen bond interactions, while salts influence the van der Waals and dispersion interactions. Energies associated with these noncovalent interactions are quantified using the fundamental molecular properties and then consolidated to comprehensively describe the hydrate phase. Finally, the proposed approach is widely tested for hydrate systems (total 30) with pure or mixed guests in the presence of single or multiple salts. Our model secures better predictions of the phase equilibria data compared with the existing methodologies.

show abstract

A reliable model to predict the methane-hydrate equilibrium: An updated database and machine learning approach

Cited by 9 publications

References 65 publications

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO₂–CH₄ Exchange: Experiments, Simulations, and Pilot Test Applications

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO₂–CH₄ Exchange: Experiments, Simulations, and Pilot Test Applications

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

Formulating Noncovalent Interactions for Gas Hydrates with Electrolytes: A New Approach of Stability Analysis

Contact Info

Product

Resources

About

A reliable model to predict the methane-hydrate equilibrium: An updated database and machine learning approach

Cited by 9 publications

References 65 publications

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO2–CH4 Exchange: Experiments, Simulations, and Pilot Test Applications

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO2–CH4 Exchange: Experiments, Simulations, and Pilot Test Applications

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

Formulating Noncovalent Interactions for Gas Hydrates with Electrolytes: A New Approach of Stability Analysis

Contact Info

Product

Resources

About

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO₂–CH₄ Exchange: Experiments, Simulations, and Pilot Test Applications

Critical Review on Carbon Dioxide Sequestration Potentiality in Methane Hydrate Reservoirs via CO₂–CH₄ Exchange: Experiments, Simulations, and Pilot Test Applications

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