1
|
Esmaeili A, Hekmatmehr H, Atashrouz S, Madani SA, Pourmahdi M, Nedeljkovic D, Hemmati-Sarapardeh A, Mohaddespour A. Insights into modeling refractive index of ionic liquids using chemical structure-based machine learning methods. Sci Rep 2023; 13:11966. [PMID: 37488224 PMCID: PMC10366230 DOI: 10.1038/s41598-023-39079-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Accepted: 07/19/2023] [Indexed: 07/26/2023] Open
Abstract
Ionic liquids (ILs) have drawn much attention due to their extensive applications and environment-friendly nature. Refractive index prediction is valuable for ILs quality control and property characterization. This paper aims to predict refractive indices of pure ILs and identify factors influencing refractive index changes. Six chemical structure-based machine learning models called eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Convolutional Neural Network (CNN), Adaptive Boosting-Decision Tree (Ada-DT), and Adaptive Boosting-Support Vector Machine (Ada-SVM) were developed to achieve this goal. An enormous dataset containing 6098 data points of 483 different ILs was exploited to train the machine learning models. Each data point's chemical substructures, temperature, and wavelength were considered for the models' inputs. Including wavelength as input is unprecedented among predictions done by machine learning methods. The results show that the best model was CatBoost, followed by XGBoost, LightGBM, Ada-DT, CNN, and Ada-SVM. The R2 and average absolute percent relative error (AAPRE) of the best model were 0.9973 and 0.0545, respectively. Comparing this study's models with the literature shows two advantages regarding the dataset's abundance and prediction accuracy. This study also reveals that the presence of the -F substructure in an ionic liquid has the most influence on its refractive index among all inputs. It was also found that the refractive index of imidazolium-based ILs increases with increasing alkyl chain length. In conclusion, chemical structure-based machine learning methods provide promising insights into predicting the refractive index of ILs in terms of accuracy and comprehensiveness.
Collapse
Affiliation(s)
- Ali Esmaeili
- Renewable Energies Engineering Department, Faculty of Mechanical and Energy Engineering, Shahid Beheshti University, Tehran, Iran
| | - Hesamedin Hekmatmehr
- Renewable Energies Engineering Department, Faculty of Mechanical and Energy Engineering, Shahid Beheshti University, Tehran, Iran
| | - Saeid Atashrouz
- Department of Chemical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran.
| | - Seyed Ali Madani
- Department of Chemical and Petroleum Engineering, University of Calgary, 2500 University Drive NW, Calgary, AB, T2N 1N4, Canada
| | - Maryam Pourmahdi
- Department of Polymer Reaction Engineering, Faculty of Chemical Engineering, Tarbiat Modares University, Tehran, Iran
| | - Dragutin Nedeljkovic
- College of Engineering and Technology, American University of the Middle East, Egaila, 54200, Kuwait
| | - Abdolhossein Hemmati-Sarapardeh
- Department of Petroleum Engineering, Shahid Bahonar University of Kerman, Kerman, Iran.
- State Key Laboratory of Continental Shale Hydrocarbon Accumulation and Efficient Development, Ministry of Education, Northeast Petroleum University, Daqing, 163318, China.
| | - Ahmad Mohaddespour
- Department of Chemical Engineering, McGill University, Montreal, QC, H3A 0C5, Canada.
| |
Collapse
|
2
|
A REVIEW OF GROUP CONTRIBUTION MODELS TO CALCULATE THERMODYNAMIC PROPERTIES OF IONIC LIQUIDS FOR PROCESS SYSTEMS ENGINEERING. Chem Eng Res Des 2022. [DOI: 10.1016/j.cherd.2022.07.033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
3
|
Sun Y, Chen M, Zhao Y, Zhu Z, Xing H, Zhang P, Zhang X, Ding Y. Machine learning assisted QSPR model for prediction of ionic liquid’s refractive index and viscosity: The effect of representations of ionic liquid and ensemble model development. J Mol Liq 2021. [DOI: 10.1016/j.molliq.2021.115970] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
4
|
Physicochemical Characterization and Simulation of the Solid-Liquid Equilibrium Phase Diagram of Terpene-Based Eutectic Solvent Systems. Molecules 2021; 26:molecules26061801. [PMID: 33806853 PMCID: PMC8004849 DOI: 10.3390/molecules26061801] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2021] [Revised: 03/17/2021] [Accepted: 03/19/2021] [Indexed: 11/16/2022] Open
Abstract
The characterization of terpene-based eutectic solvent systems is performed to describe their solid-liquid phase transitions. Physical properties are measured experimentally and compared to computed correlations for deep eutectic solvents (DES) and the percentage relative error er for the density, surface tension, and refractive index is obtained. The thermodynamic parameters, including the degradation, glass transition and crystallization temperatures, are measured using DSC and TGA. Based on these data, the solid-liquid equilibrium phase diagrams are calculated for the ideal case and predictions are made using the semi-predictive UNIFAC and the predictive COSMO RS models, the latter with two different parametrization levels. For each system, the ideal, experimental, and predicted eutectic points are obtained. The deviation from ideality is observed experimentally and using the thermodynamic models for Thymol:Borneol and Thymol:Camphor. In contrast, a negative deviation is observed only experimentally for Menthol:Borneol and Menthol:Camphor. Moreover, the chemical interactions are analyzed using FTIR and 1H-NMR to study the intermolecular hydrogen bonding in the systems.
Collapse
|
5
|
Ding Y, Chen M, Guo C, Zhang P, Wang J. Molecular fingerprint-based machine learning assisted QSAR model development for prediction of ionic liquid properties. J Mol Liq 2021. [DOI: 10.1016/j.molliq.2020.115212] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
6
|
Zhu P, Kang X, Latif U, Gong M, Zhao Y. A Reliable Database for Ionic Volume and Surface: Its Application To Predict Molar Volume and Density of Ionic Liquid. Ind Eng Chem Res 2019. [DOI: 10.1021/acs.iecr.9b00720] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Affiliation(s)
- Peng Zhu
- School of Materials Science and Energy Engineering, Foshan University, Foshan, Guangdong 528000, China
| | - Xuejing Kang
- School of Material and Chemical Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China
| | - Ullah Latif
- Beijing Key Laboratory of Ionic Liquids Clean Process, CAS Key Laboratory of Green Process and Engineering, State Key Laboratory of Multiphase Complex Systems, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China
| | - Maoming Gong
- Beijing Key Laboratory of Ionic Liquids Clean Process, CAS Key Laboratory of Green Process and Engineering, State Key Laboratory of Multiphase Complex Systems, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China
| | - Yongsheng Zhao
- Department of Chemical Engineering, University of California, Santa Barbara, California 93106-5080, United States
| |
Collapse
|
7
|
Venkatraman V, Raj JJ, Evjen S, Lethesh KC, Fiksdahl A. In silico prediction and experimental verification of ionic liquid refractive indices. J Mol Liq 2018. [DOI: 10.1016/j.molliq.2018.05.067] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
|