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
|
Duong DV, Tran HV, Pathirannahalage SK, Brown SJ, Hassett M, Yalcin D, Meftahi N, Christofferson AJ, Greaves TL, Le TC. Machine learning investigation of viscosity and ionic conductivity of protic ionic liquids in water mixtures. J Chem Phys 2022; 156:154503. [PMID: 35459305 DOI: 10.1063/5.0085592] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/16/2023] Open
Abstract
Ionic liquids (ILs) are well classified as designer solvents based on the ease of tailoring their properties through modifying the chemical structure of the cation and anion. However, while many structure-property relationships have been developed, these generally only identify the most dominant trends. Here, we have used machine learning on existing experimental data to construct robust models to produce meaningful predictions across a broad range of cation and anion chemical structures. Specifically, we used previously collated experimental data for the viscosity and conductivity of protic ILs [T. L. Greaves and C. J. Drummond, Chem. Rev. 115, 11379-11448 (2015)] as the inputs for multiple linear regression and neural network models. These were then used to predict the properties of all 1827 possible cation-anion combinations (excluding the input combinations). These models included the effect of water content of up to 5 wt. %. A selection of ten new protic ILs was then prepared, which validated the usefulness of the models. Overall, this work shows that relatively sparse data can be used productively to predict physicochemical properties of vast arrays of ILs.
Collapse
Affiliation(s)
- Dung Viet Duong
- School of Engineering, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia
| | - Hung-Vu Tran
- Department of Chemistry, University of Houston, 4800 Calhoun Road, Houston, Texas 77204-5003, USA
| | | | - Stuart J Brown
- School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia
| | - Michael Hassett
- School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia
| | - Dilek Yalcin
- CSIRO Manufacturing, Clayton, VIC 3168, Australia
| | - Nastaran Meftahi
- ARC Centre of Excellence in Exciton Science, School of Science, RMIT University, Melbourne, VIC 3001, Australia
| | - Andrew J Christofferson
- School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia
| | - Tamar L Greaves
- School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia
| | - Tu C Le
- School of Engineering, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia
| |
Collapse
|
3
|
Greaves TL, Schaffarczyk McHale KS, Burkart-Radke RF, Harper JB, Le TC. Machine learning approaches to understand and predict rate constants for organic processes in mixtures containing ionic liquids. Phys Chem Chem Phys 2021; 23:2742-2752. [PMID: 33496292 DOI: 10.1039/d0cp04227g] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/06/2023]
Abstract
The ability to tailor the constituent ions in ionic liquids (ILs) is highly advantageous as it provides access to solvents with a range of physicochemical properties. However, this benefit also leads to large compositional spaces that need to be explored to optimise systems, often involving time consuming experimental work. The use of machine learning methods is an effective way to gain insight based on existing data, to develop structure-property relationships and to allow the prediction of ionic liquid properties. Here we have applied machine learning models to experimentally determined rate constants of a representative organic process (the reaction of pyridine with benzyl bromide) in IL-acetonitrile mixtures. Multiple linear regression (MLREM) and artificial neural networks (BRANNLP) were both able to model the data well. The MLREM model was able to identify the structural features on the cations and anions that had the greatest effect on the rate constant. Secondly, predictive MLREM and BRANNLP models were developed from the full initial set of rate constant data. From these models, a large number of predictions (>9000) of rate constant were made for mixtures of different ionic liquids, at different proportions of ionic liquid and molecular solvent, at different temperatures. A selection of these predictions were tested experimentally, including through the preparation of novel ionic liquids, with overall good agreement between the predicted and experimental data. This study highlights the benefits of using machine learning methods on kinetic data in ionic liquid mixtures to enable the development of rigorous structure-property relationships across multiple variables simultaneously, and to predict properties of new ILs and experimental conditions.
Collapse
Affiliation(s)
- Tamar L Greaves
- College of Science Engineering and Health, RMIT University, Melbourne, VIC 3001, Australia.
| | | | | | - Jason B Harper
- School of Chemistry, University of New South Wales, Sydney, NSW 2052, Australia.
| | - Tu C Le
- College of Science Engineering and Health, RMIT University, Melbourne, VIC 3001, Australia.
| |
Collapse
|
4
|
Zimmermann AS, Mattedi S. Density and speed of sound prediction for binary mixtures of water and ammonium-based ionic liquids using feedforward and cascade forward neural networks. J Mol Liq 2020. [DOI: 10.1016/j.molliq.2020.113212] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
|
5
|
The analysis of liquid–liquid equilibria (LLE) of toluene + heptane + ionic liquid ternary mixture using intelligent models. Chem Eng Res Des 2018. [DOI: 10.1016/j.cherd.2017.12.029] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
6
|
Moghadam M, Asgharzadeh S. On the application of artificial neural network for modeling liquid-liquid equilibrium. J Mol Liq 2016. [DOI: 10.1016/j.molliq.2016.04.098] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
7
|
Shehada N, Cancilla JC, Torrecilla JS, Pariente ES, Brönstrup G, Christiansen S, Johnson DW, Leja M, Davies MPA, Liran O, Peled N, Haick H. Silicon Nanowire Sensors Enable Diagnosis of Patients via Exhaled Breath. ACS NANO 2016; 10:7047-57. [PMID: 27383408 DOI: 10.1021/acsnano.6b03127] [Citation(s) in RCA: 105] [Impact Index Per Article: 13.1] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/23/2023]
Abstract
Two of the biggest challenges in medicine today are the need to detect diseases in a noninvasive manner and to differentiate between patients using a single diagnostic tool. The current study targets these two challenges by developing a molecularly modified silicon nanowire field effect transistor (SiNW FET) and showing its use in the detection and classification of many disease breathprints (lung cancer, gastric cancer, asthma, and chronic obstructive pulmonary disease). The fabricated SiNW FETs are characterized and optimized based on a training set that correlate their sensitivity and selectivity toward volatile organic compounds (VOCs) linked with the various disease breathprints. The best sensors obtained in the training set are then examined under real-world clinical conditions, using breath samples from 374 subjects. Analysis of the clinical samples show that the optimized SiNW FETs can detect and discriminate between almost all binary comparisons of the diseases under examination with >80% accuracy. Overall, this approach has the potential to support detection of many diseases in a direct harmless way, which can reassure patients and prevent numerous unpleasant investigations.
Collapse
Affiliation(s)
- Nisreen Shehada
- Department of Chemical Engineering and Russell Berrie Nanotechnology Institute, Technion-Israel Institute of Technology , Haifa 3200003, Israel
| | - John C Cancilla
- Department of Chemical Engineering, Complutense University of Madrid , Madrid 28040, Spain
| | - Jose S Torrecilla
- Department of Chemical Engineering, Complutense University of Madrid , Madrid 28040, Spain
| | - Enrique S Pariente
- Department of Chemical Engineering, Complutense University of Madrid , Madrid 28040, Spain
| | - Gerald Brönstrup
- Max-Planck-Institute for the Science of Light , Günther-Scharowsky-Strasse 1, Erlangen 91058, Germany
| | - Silke Christiansen
- Max-Planck-Institute for the Science of Light , Günther-Scharowsky-Strasse 1, Erlangen 91058, Germany
- Helmholtz-Zentrum Berlin für Materialien und Energie GmbH , Hahn-Meitner-Platz 1, 14109 Berlin, Germany
| | - Douglas W Johnson
- Florida Radiation Oncology Group, Department of Radiation Oncology, Baptist Cancer Institute (BCI) , 1235 San Marco Boulevard., Suite 100, Jacksonville, Florida 32207, United States
| | - Marcis Leja
- Faculty of Medicine, University of Latvia , 19 Raiņa boulv., LV1586 Riga, Latvia
- Department of Research, Riga East University Hospital , 6 Linezera iela, LV1006 Riga, Latvia
- Digestive Diseases Centre GASTRO , Riga, Latvia. 6 Linezera iela, LV1006 Riga, Latvia
| | - Michael P A Davies
- Molecular & Clinical Cancer Medicine, University of Liverpool , William Duncan Building, 6 West Derby Street, Liverpool L7 8TX, United Kingdom
| | - Ori Liran
- Thoracic Cancer Unit, Davidoff cancer center, Petah Tiqwa and the Tel Aviv University , Tel Aviv, Israel
| | - Nir Peled
- Thoracic Cancer Unit, Davidoff cancer center, Petah Tiqwa and the Tel Aviv University , Tel Aviv, Israel
| | - Hossam Haick
- Department of Chemical Engineering and Russell Berrie Nanotechnology Institute, Technion-Israel Institute of Technology , Haifa 3200003, Israel
| |
Collapse
|
8
|
Cancilla JC, Perez A, Wierzchoś K, Torrecilla JS. Neural networks applied to determine the thermophysical properties of amino acid based ionic liquids. Phys Chem Chem Phys 2016; 18:7435-41. [DOI: 10.1039/c5cp07649h] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
A series of models based on artificial neural networks (ANNs) have been designed to estimate the thermophysical properties of different amino acid-based ionic liquids (AAILs).
Collapse
Affiliation(s)
- John C. Cancilla
- Departamento de Ingeniería Química
- Facultad de Ciencias Químicas
- Universidad Complutense de Madrid
- 28040-Madrid
- Spain
| | - Ana Perez
- Departamento de Ingeniería Química
- Facultad de Ciencias Químicas
- Universidad Complutense de Madrid
- 28040-Madrid
- Spain
| | | | - José S. Torrecilla
- Departamento de Ingeniería Química
- Facultad de Ciencias Químicas
- Universidad Complutense de Madrid
- 28040-Madrid
- Spain
| |
Collapse
|