Can I read Exploring the Power of Machine Learning in Analyzing the Gas Minimum Miscibility Pressure in Hydrocarbons on EtoBox?

Exploring the Power of Machine Learning in Analyzing the Gas Minimum Miscibility Pressure in Hydrocarbons by Mahsheed Rayhani; Afshin Tatar; Amin Shokrollahi; Abbas Zeinijahromi is a Engineering article available to read on EtoBox.

What is Exploring the Power of Machine Learning in Analyzing the Gas Minimum Miscibility Pressure in Hydrocarbons about?

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,

Who reads Exploring the Power of Machine Learning in Analyzing the Gas Minimum Miscibility Pressure in Hydrocarbons?

Author

Mahsheed Rayhani; Afshin Tatar; Amin Shokrollahi; Abbas Zeinijahromi

Publisher

Elsevier BV

Published

2023

Language

EN

Field

Engineering (Physical Sciences)