New insight into viscosity prediction of imidazolium-based ionic liquids and their mixtures with machine learning models DOI

Amir Hossein Sheikhshoaei,

Ali Sanati

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 25, 2025

Abstract Ionic liquids (ILs) as eco-friendly solvents have attracted particular attention in various fields of science including the petroleum industry. Among different families ILs, imidazolium-based ILs been subject many research studies. However, not enough experimental studies were conducted to determine viscosity this family ILs. Therefore, accurate prediction is crucial for their practical applications. This study aims predict and mixtures using critical properties these input parameters. To achieve this, machine learning (ML) models implemented. Furthermore, performance ML predicting IL was compared with a Molecular-based model, ePC-SAFT-FVT (ePC-FVT-MB), an Ion-based (ePC-FVT-MB). Graphical statistical analyses revealed that RF model offers lowest error pure while CatBoost performs best mixtures. In addition, sensitivity analysis showed decreases temperature increases pressure. The proposed exhibit high accuracy under varying conditions. Outlier detection Leverage method indicated 95.11% data 94.92% mixed are statistically valid.

Language: Английский

Integrating Machine Learning-Based Classification and Regression Models for Solvent Regeneration Prediction in Post-Combustion Carbon Capture: An Absorption-Based Case DOI Creative Commons
Farzin Hosseinifard, Mostafa Setak, Majid Amidpour

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104856 - 104856

Published: April 1, 2025

Language: Английский

Citations

0
New insight into viscosity prediction of imidazolium-based ionic liquids and their mixtures with machine learning models DOI

Amir Hossein Sheikhshoaei,

Ali Sanati

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 25, 2025

Abstract Ionic liquids (ILs) as eco-friendly solvents have attracted particular attention in various fields of science including the petroleum industry. Among different families ILs, imidazolium-based ILs been subject many research studies. However, not enough experimental studies were conducted to determine viscosity this family ILs. Therefore, accurate prediction is crucial for their practical applications. This study aims predict and mixtures using critical properties these input parameters. To achieve this, machine learning (ML) models implemented. Furthermore, performance ML predicting IL was compared with a Molecular-based model, ePC-SAFT-FVT (ePC-FVT-MB), an Ion-based (ePC-FVT-MB). Graphical statistical analyses revealed that RF model offers lowest error pure while CatBoost performs best mixtures. In addition, sensitivity analysis showed decreases temperature increases pressure. The proposed exhibit high accuracy under varying conditions. Outlier detection Leverage method indicated 95.11% data 94.92% mixed are statistically valid.

Language: Английский

Citations

0