FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362603033> ?p ?o ?g. }

• W4362603033 endingPage "211778" @default.
• W4362603033 startingPage "211778" @default.
• W4362603033 abstract "Minimum Miscibility Pressure (MMP) plays a crucial role in subsurface gas injection processes. Hence, the accurate determination and analysis of the effective parameters on MMP are vital for a successful injection project. In this study, different Machine Learning (ML) algorithms are used to identify the most influential parameters on the MMP and develop reliable predictive models. A comprehensive database containing 812 samples (almost all the available experimental data set published from 1961 to 2022) is collected from 66 open literature studies. Six algorithms were employed for feature selection: Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), Sequential Forward Floating Selection (SFFS), Sequential Backward Floating Selection (SBFS), Lasso Regression (LR), and Random Forest Feature Importance (RFFI). These feature selection algorithms were evaluated using a Decision Tree (DT) regressor. The most important features from 42 potential features were x C₅, x C₆, x C₂-C₆, MW C₇⁺, MW Gas, TC, and T, selected using the SBFS method based on the Root Mean Squared Error (RMSE). Using the best-selected features, six predictive models were developed, including LR, DT, Random Forest (RF), Extra Trees (ET), Stacking Regressor (SR), and Voting Regressor (VR). The SR predictive model performed the best with RMSE and R2 values of 18.37 bars and 0.96, respectively, for the testing dataset. The outcomes of this research can be employed for any industrial process involving gas injection into hydrocarbon reservoirs to select the most relevant features in designing the experimental and field trials." @default.
• W4362603033 created "2023-04-06" @default.
• W4362603033 creator A5004033179 @default.
• W4362603033 creator A5015755122 @default.
• W4362603033 creator A5031808164 @default.
• W4362603033 creator A5058641647 @default.
• W4362603033 date "2023-07-01" @default.
• W4362603033 modified "2023-10-18" @default.
• W4362603033 title "Exploring the power of machine learning in analyzing the gas minimum miscibility pressure in hydrocarbons" @default.
• W4362603033 cites W1933450155 @default.
• W4362603033 cites W1964186109 @default.
• W4362603033 cites W1965427963 @default.
• W4362603033 cites W1965775669 @default.
• W4362603033 cites W1980994638 @default.
• W4362603033 cites W1985600426 @default.
• W4362603033 cites W1989649557 @default.
• W4362603033 cites W1990420872 @default.
• W4362603033 cites W1996324466 @default.
• W4362603033 cites W1997783064 @default.
• W4362603033 cites W1997962051 @default.
• W4362603033 cites W2006374398 @default.
• W4362603033 cites W2009343133 @default.
• W4362603033 cites W2010044158 @default.
• W4362603033 cites W2011301426 @default.
• W4362603033 cites W2014915963 @default.
• W4362603033 cites W2015378812 @default.
• W4362603033 cites W2016187546 @default.
• W4362603033 cites W2017427082 @default.
• W4362603033 cites W2017760436 @default.
• W4362603033 cites W2025797714 @default.
• W4362603033 cites W2027838767 @default.
• W4362603033 cites W2040182540 @default.
• W4362603033 cites W2043308012 @default.
• W4362603033 cites W2044833557 @default.
• W4362603033 cites W2048626655 @default.
• W4362603033 cites W2051222413 @default.
• W4362603033 cites W2051890803 @default.
• W4362603033 cites W2052259071 @default.
• W4362603033 cites W2054337500 @default.
• W4362603033 cites W2055929657 @default.
• W4362603033 cites W2072026441 @default.
• W4362603033 cites W2074435123 @default.
• W4362603033 cites W2079597494 @default.
• W4362603033 cites W2082087356 @default.
• W4362603033 cites W2087623443 @default.
• W4362603033 cites W2095366764 @default.
• W4362603033 cites W2102543001 @default.
• W4362603033 cites W2120216197 @default.
• W4362603033 cites W2157043635 @default.
• W4362603033 cites W2160904652 @default.
• W4362603033 cites W2165669763 @default.
• W4362603033 cites W2170336234 @default.
• W4362603033 cites W2177477571 @default.
• W4362603033 cites W2227883226 @default.
• W4362603033 cites W2259661008 @default.
• W4362603033 cites W2313317342 @default.
• W4362603033 cites W2322970423 @default.
• W4362603033 cites W2444108988 @default.
• W4362603033 cites W2460103999 @default.
• W4362603033 cites W2473683835 @default.
• W4362603033 cites W2489377329 @default.
• W4362603033 cites W2495979836 @default.
• W4362603033 cites W2559954194 @default.
• W4362603033 cites W2602419731 @default.
• W4362603033 cites W2618598738 @default.
• W4362603033 cites W2735245818 @default.
• W4362603033 cites W2791412786 @default.
• W4362603033 cites W2791718738 @default.
• W4362603033 cites W2799462250 @default.
• W4362603033 cites W2810569510 @default.
• W4362603033 cites W2888286626 @default.
• W4362603033 cites W2888812182 @default.
• W4362603033 cites W2891005831 @default.
• W4362603033 cites W2891198675 @default.
• W4362603033 cites W2944461858 @default.
• W4362603033 cites W2946091792 @default.
• W4362603033 cites W2953379322 @default.
• W4362603033 cites W2955421531 @default.
• W4362603033 cites W2969884459 @default.
• W4362603033 cites W2973817809 @default.
• W4362603033 cites W2978693217 @default.
• W4362603033 cites W2989774988 @default.
• W4362603033 cites W2993482125 @default.
• W4362603033 cites W3020453448 @default.
• W4362603033 cites W3033983598 @default.
• W4362603033 cites W3099878876 @default.
• W4362603033 cites W3117891459 @default.
• W4362603033 cites W3124626644 @default.
• W4362603033 cites W3198769004 @default.
• W4362603033 cites W3208060164 @default.
• W4362603033 cites W3214886480 @default.
• W4362603033 cites W4288969894 @default.
• W4362603033 cites W4321768923 @default.
• W4362603033 doi "https://doi.org/10.1016/j.geoen.2023.211778" @default.
• W4362603033 hasPublicationYear "2023" @default.
• W4362603033 type Work @default.
• W4362603033 citedByCount "1" @default.
• W4362603033 countsByYear W43626030332023 @default.

• next