Modeling of gas hydrate phase equilibria: Extremely randomized trees and LSSVM approaches

Yarveicy, Hamidreza; Ghiasi, Mohammad M.

doi:10.1016/j.molliq.2017.08.053

Cited by 74 publications

(19 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zargari et al established a nonlinear prediction model of hydrate formation temperature using an adaptive neurofuzzy reasoning system . Subsequently, Yarveicy and Ghiasi used the extra trees algorithm to estimate the conditions for hydrate formation/dissociation of different gases in different water-based solutions …”

Section: Introductionmentioning

confidence: 99%

Stability and NMR Chemical Shift of Amorphous Precursors of Methane Hydrate: Insights from Dispersion-Corrected Density Functional Theory Calculations Combined with Machine Learning

Wang

Tang

et al. 2020

J. Phys. Chem. B

View full text Add to dashboard Cite

Clathrate hydrates of natural gases are important backup energy sources. It is thus of great significance to explore the nucleation process of hydrates. Hydrate clusters are building blocks of crystalline hydrates and represent the initial stage of hydrate nucleation. Using dispersion-corrected density functional theory (DFT-D) combined with machine learning, herein, we systematically investigate the evolution of stabilities and nuclear magnetic resonance (NMR) chemical shifts of amorphous precursors from monocage clusters CH4(H2O) n (n = 16–24) to decacage clusters (CH4)10(H2O) n (n = 121–125). Compared with planelike configurations, the close-packed structures formed by the water-cage clusters are energetically favorable. The 512 cages are dominant, and the emerging amorphous precursors may be part of sII hydrates at the initial stage of nucleation. Based on our data set, the possible initial fusion pathways for water-cage clusters are proposed. In addition, the 13C NMR chemical shifts for encapsulated methane molecules also showed regular changes during the fusion of water-cage clusters. Machine learning can reproduce the DFT-D results well, providing a structure–energy-property landscape that could be used to predict the energy and NMR chemical shifts of such multicages with more water molecules. These theoretical results present vital insights into the hydrate nucleation from a unique perspective.

show abstract

Section: Introductionmentioning

confidence: 99%

Stability and NMR Chemical Shift of Amorphous Precursors of Methane Hydrate: Insights from Dispersion-Corrected Density Functional Theory Calculations Combined with Machine Learning

Wang

Tang

et al. 2020

J. Phys. Chem. B

View full text Add to dashboard Cite

show abstract

“…It is an ice-like, non-stochiometric crystalline mixture made up of a water cage frame dominated by gas molecules like methane, CH4, ethane, C2H5, and carbon dioxide, CO2, that forms solid particles that takes place under high pressure and low temperature conditions [3][4][5][6]. Gas hydrates are produced in the petroleum and natural gas industries' output, refining and transmission facilities [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Application of Gaussian Process Regression (GPR) in Gas Hydrate Mitigation

Suresh

Qasim

Lal

et al. 2021

ARFMTS

View full text Add to dashboard Cite

The production of oil and natural gas contributes to a significant amount of revenue generation in Malaysia thereby strengthening the country’s economy. The flow assurance industry is faced with impediments during smooth operation of the transmission pipeline in which gas hydrate formation is the most important. It affects the normal operation of the pipeline by plugging it. Under high pressure and low temperature conditions, gas hydrate is a crystalline structure consisting of a network of hydrogen bonds between host molecules of water and guest molecules of the incoming gases. Industry uses different types of chemical inhibitors in pipeline to suppress hydrate formation. To overcome this problem, machine learning algorithm has been introduced as part of risk management strategies. The objective of this paper is to utilize Machine Learning (ML) model which is Gaussian Process Regression (GPR). GPR is a new approach being applied to mitigate the growth of gas hydrate. The input parameters used are concentration and pressure of Carbon Dioxide (CO2) and Methane (CH4) gas hydrates whereas the output parameter is the Average Depression Temperature (ADT). The values for the parameter are taken from available data sets that enable GPR to predict the results accurately in terms of Coefficient of Determination, R2 and Mean Squared Error, MSE. The outcome from the research showed that GPR model provided with highest R2 value for training and testing data of 97.25% and 96.71%, respectively. MSE value for GPR was also found to be lowest for training and testing data of 0.019 and 0.023, respectively.

show abstract

“…Yarveicy et al proposed a novel algorithm (least-squares support vector machine, LSSVM) based on machine learning for hydrate formation prediction. To evaluate the model performance, they compared the predicted value with a mass of experimental data from the literature, and the result showed a wide range of applicability and high accuracy of the model …”

Section: Introductionmentioning

confidence: 99%

“…To evaluate the model performance, they compared the predicted value with a mass of experimental data from the literature, and the result showed a wide range of applicability and high accuracy of the model. 23 In previous experiments investigating hydrate phase equilibrium conditions in porous sediments, either the experimental gas was pure CH 4 gas or the brine was just NaCl solution, or the sediments were artificially prepared single/mixed media. However, it is difficult to reflect the phase equilibrium conditions of gas hydrates in real seafloor sediments.…”

Section: Introductionmentioning

confidence: 99%

Phase Equilibria of Natural Gas Hydrates in Bulk Brine and Marine Sediments from the South China Sea

et al. 2021

View full text Add to dashboard Cite

Studies on gas hydrate phase equilibrium conditions are reported widely in the literature. However, the data available for natural gas hydrates (NGHs) in real marine conditions are limited. In this study, NGH dissociation conditions in bulk brine and marine sediments were measured by using a microdifferential scanning calorimetry (μ-DSC). The sediments used in the experiment were obtained from the Shenhu area of the South China Sea, and the natural gas, as well as part of the water samples, were prepared according to the field data. Additionally, the Chen-Guo model was improved to calculate the NGH equilibrium conditions in the systems containing electrolytes and porous sediments. The experimental results showed that the NGH is relatively more stable than pure CH 4 hydrate. The hydrate phase equilibrium curves shift to the left with the increased salinity in bulk water and sediments. In addition, the hydrate decomposition temperatures in marine sediments are obviously lower than those in bulk water. The average deviations of the improved model are 2.32% and 3.7% for bulk brine and sediments, respectively, which indicates great predictability. We consider that besides pore size as the main factor affecting the hydrate phase equilibrium, the water absorption capacity of marine sediments can also affect their decomposition conditions. The hydrate decomposition enthalpies were calculated by the Clausius−Clapeyron equation, and the results showed that the enthalpies increased with the decreased salinity and the addition of marine sediments. These findings are significant to NGH production safety in real marine sediments.

show abstract

Modeling of gas hydrate phase equilibria: Extremely randomized trees and LSSVM approaches

Cited by 74 publications

References 67 publications

Stability and NMR Chemical Shift of Amorphous Precursors of Methane Hydrate: Insights from Dispersion-Corrected Density Functional Theory Calculations Combined with Machine Learning

Stability and NMR Chemical Shift of Amorphous Precursors of Methane Hydrate: Insights from Dispersion-Corrected Density Functional Theory Calculations Combined with Machine Learning

Application of Gaussian Process Regression (GPR) in Gas Hydrate Mitigation

Phase Equilibria of Natural Gas Hydrates in Bulk Brine and Marine Sediments from the South China Sea

Contact Info

Product

Resources

About