Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102678881> ?p ?o ?g. }
- W3102678881 endingPage "112894" @default.
- W3102678881 startingPage "112894" @default.
- W3102678881 abstract "Gas hydrates have significant applications in the areas of natural gas storage, desalination and gas separation. Knowledge of the thermodynamic conditions associated with hydrate formation is critical to their synthesis. Presently, we use machine learning (ML) to train and evaluate the performance of three algorithms on an experimental database (>1800 data points) to predict hydrate dissociation temperatures as a function of the constituent hydrate precursors and inhibitors. Importantly, and in contrast to most previous studies, we use thermodynamic variables such as the activity-based contribution due to electrolytes, partial pressure of individual gases, and specific gravity of the overall mixture as input features in the prediction algorithms. Using such features results in more physics-aware ML algorithms, which can capture the individual contributions of gases and electrolytes in a more fundamental manner. Three ML algorithms, Random Forest (RF), Extra Trees (ET), and Extreme Gradient Boosting (XGBoost) are employed and demonstrate excellent accuracy in their predictions of hydrate equilibrium conditions. The overall coefficient of determination (R2) percentage is greater than 97% for all the ML models. XGBoost outperforms RF and ET with the highest overall coefficient of determination (R2) and the lowest overall Average Absolute relative deviation (AARD) of 99.56% and 0.086% respectively." @default.
- W3102678881 created "2020-11-23" @default.
- W3102678881 creator A5015104486 @default.
- W3102678881 creator A5085325272 @default.
- W3102678881 date "2021-02-01" @default.
- W3102678881 modified "2023-10-14" @default.
- W3102678881 title "Thermodynamic features-driven machine learning-based predictions of clathrate hydrate equilibria in the presence of electrolytes" @default.
- W3102678881 cites W1965097275 @default.
- W3102678881 cites W1965511539 @default.
- W3102678881 cites W1968078579 @default.
- W3102678881 cites W1972397789 @default.
- W3102678881 cites W1973309453 @default.
- W3102678881 cites W1986014872 @default.
- W3102678881 cites W1988253774 @default.
- W3102678881 cites W1990340486 @default.
- W3102678881 cites W1990742291 @default.
- W3102678881 cites W1991402462 @default.
- W3102678881 cites W1994196683 @default.
- W3102678881 cites W1995900045 @default.
- W3102678881 cites W1997396742 @default.
- W3102678881 cites W1999892228 @default.
- W3102678881 cites W2005724369 @default.
- W3102678881 cites W2008238389 @default.
- W3102678881 cites W2009646514 @default.
- W3102678881 cites W2010798895 @default.
- W3102678881 cites W2011811840 @default.
- W3102678881 cites W2011846307 @default.
- W3102678881 cites W2015224219 @default.
- W3102678881 cites W2019622755 @default.
- W3102678881 cites W2021002342 @default.
- W3102678881 cites W2026633521 @default.
- W3102678881 cites W2028070629 @default.
- W3102678881 cites W2029187433 @default.
- W3102678881 cites W2036599383 @default.
- W3102678881 cites W2038005399 @default.
- W3102678881 cites W2038380745 @default.
- W3102678881 cites W2039921149 @default.
- W3102678881 cites W2039935529 @default.
- W3102678881 cites W2044221988 @default.
- W3102678881 cites W2045930597 @default.
- W3102678881 cites W2046541993 @default.
- W3102678881 cites W2046593516 @default.
- W3102678881 cites W2056132907 @default.
- W3102678881 cites W2056188184 @default.
- W3102678881 cites W2061593639 @default.
- W3102678881 cites W2062998805 @default.
- W3102678881 cites W2067307291 @default.
- W3102678881 cites W2075368773 @default.
- W3102678881 cites W2079112666 @default.
- W3102678881 cites W2091123923 @default.
- W3102678881 cites W2092362006 @default.
- W3102678881 cites W2096692469 @default.
- W3102678881 cites W2105730493 @default.
- W3102678881 cites W2112617880 @default.
- W3102678881 cites W2113242816 @default.
- W3102678881 cites W2120529575 @default.
- W3102678881 cites W2137109053 @default.
- W3102678881 cites W2143277719 @default.
- W3102678881 cites W2150785911 @default.
- W3102678881 cites W2155430429 @default.
- W3102678881 cites W2158128782 @default.
- W3102678881 cites W2161455714 @default.
- W3102678881 cites W2162086856 @default.
- W3102678881 cites W2196371488 @default.
- W3102678881 cites W2203978601 @default.
- W3102678881 cites W2233098019 @default.
- W3102678881 cites W2521254122 @default.
- W3102678881 cites W2526289442 @default.
- W3102678881 cites W2750473668 @default.
- W3102678881 cites W2886564934 @default.
- W3102678881 cites W2896096896 @default.
- W3102678881 cites W2911964244 @default.
- W3102678881 cites W2925242208 @default.
- W3102678881 cites W2945601520 @default.
- W3102678881 cites W2960605475 @default.
- W3102678881 cites W2996685490 @default.
- W3102678881 cites W3003400711 @default.
- W3102678881 cites W3012105271 @default.
- W3102678881 cites W338159216 @default.
- W3102678881 cites W4212883601 @default.
- W3102678881 cites W4246573237 @default.
- W3102678881 doi "https://doi.org/10.1016/j.fluid.2020.112894" @default.
- W3102678881 hasPublicationYear "2021" @default.
- W3102678881 type Work @default.
- W3102678881 sameAs 3102678881 @default.
- W3102678881 citedByCount "12" @default.
- W3102678881 countsByYear W31026788812021 @default.
- W3102678881 countsByYear W31026788812022 @default.
- W3102678881 countsByYear W31026788812023 @default.
- W3102678881 crossrefType "journal-article" @default.
- W3102678881 hasAuthorship W3102678881A5015104486 @default.
- W3102678881 hasAuthorship W3102678881A5085325272 @default.
- W3102678881 hasBestOaLocation W31026788811 @default.
- W3102678881 hasConcept C100402318 @default.
- W3102678881 hasConcept C102931765 @default.
- W3102678881 hasConcept C121332964 @default.
- W3102678881 hasConcept C147789679 @default.
- W3102678881 hasConcept C170961132 @default.