Machine learning assisted Structure-based models for predicting electrical conductivity of ionic liquids

Nakhaei-Kohani, Reza; Madani, Seyed Ali; Mousavi, Seyed-Pezhman; Atashrouz, Saeid; Abedi, Ali; Hemmati-Sarapardeh, Abdolhossein; Mohaddespour, Ahmad

doi:10.1016/j.molliq.2022.119509

Cited by 25 publications

(12 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Electrical conductivity is an important parameter to evaluate the potential application of ILs. The effects of the various IL structural components, such as cation type, anion type, functional groups, and hydrocarbon chain length, on the electrical conductivity of ionic liquids were deeply discussed. ,, …”

Section: Results and Discussionmentioning

confidence: 99%

“…With a increasing interest of ILs in electrochemistry, a systematic knowledge of electrical conductivity and ESW is of great importance. The relationship between electrical conductivity ,, or ESW − and various structural parameters such as cation type, anion type, hydrocarbon chain length, and functional groups was comprehensively discussed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Experimental and DFT Studies on Electrochemical Performances of Ester-Containing Vinylimidazolium Ionic Liquids: Effect of the Ester Substituent and Anion

Deng

Shen

et al. 2023

J. Chem. Eng. Data

View full text Add to dashboard Cite

Four imidazolium ionic liquids (ILs) with vinyl and ester groups were synthesized and characterized by 1H NMR, 13C NMR, and element analysis. The refractive index, electrical conductivity (EC), and electrochemical stability window (ESW) of the ILs were determined. The effect of the alkyl chain length of the ester group and anions on electrochemical properties was analyzed by density functional theory (DFT) calculations. At the same temperatures, the EC of the ILs decreased with the increase of the alkyl chain length. The ester group and vinyl group of cations showed a negative effect on the EC. The ESW increased with the increase of the alkyl chain length. The introduction of the ester group and vinyl group decreased the cathodic limiting potential of ester-based vinylimidazolium cations. DFT simulations showed that the structure of the IL was closely related to the EC and ESW. The average hydrogen bond length increased with the increase of the alkyl chain length of the ester group. The absolute interaction energy of ILs decreased with the increase of the alkyl chain length. Introduction of the vinyl group and ester group into the imidazolium cation resulted in a stronger cation–anion interaction, strengthening the ion mobility and charge transfer, resulting in a lower EC. The information is useful for the design and optimization of ILs as electrolytes for energy storage applications.

show abstract

Section: Results and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Experimental and DFT Studies on Electrochemical Performances of Ester-Containing Vinylimidazolium Ionic Liquids: Effect of the Ester Substituent and Anion

Deng

Shen

et al. 2023

J. Chem. Eng. Data

View full text Add to dashboard Cite

show abstract

“…Recently, Nakhaei-Kohani et al developed four ML models with descriptors based on chemical structure and thermodynamic properties, achieving similar accuracy (R 2 = 0.99, RMSE = 0.24) to our GNN+ML models. 19 Obviously, our GNNgenerated descriptors are automatically generated and easy to implement, leading to faster predictions while maintaining excellent accuracy. Therefore, our GNN+ML models with the GNN-based descriptors exhibit strong generalization and provide robust prediction capability for the ionic conductivity of ILs.…”

Section: ■ Computational Detailsmentioning

confidence: 99%

“…Such differences can be explained by the fact that the temperature has a more pronounced impact on the lower molecular weight cations and anions in this ammonium-based IL. 19 ■…”

Section: ■ Computational Detailsmentioning

confidence: 99%

“…At present, different kinds of computational models for the ionic conductivity of ILs have been proposed, mainly including molecular dynamics simulations, , group contribution method, − volume-based thermodynamics approach, and machine learning (ML) model. − Compared to traditional theoretical approaches, the data-driven ML model is naturally a statistics-based method, which often provides an accurate and efficient prediction of various properties of molecules and materials without high computational cost and electronic structure calculations. Up to now, many ML models have been widely used to predict the ionic conductivity of ILs, such as multiple linear regression (MLR), extreme gradient boosting (XGBoost), artificial neural networks (ANNs), support vector machine (SVM), , and random forest (RF) . Besides the ML model, choosing appropriate descriptors for cations and anions in ILs is a critical factor for accurately predicting their ionic conductivity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Large-Scale Screening for High Conductivity Ionic Liquids via Machine Learning Algorithm Utilizing Graph Neural Network-Based Features

Song,

Wang,

Fang

et al. 2024

J. Chem. Eng. Data

View full text Add to dashboard Cite

Ionic conductivity is a crucial parameter in the electrochemical applications of ionic liquids (ILs). Conventional methods to obtain this parameter, i.e., experimental measurements or theoretical calculations, are time-consuming and resourceintensive. Herein, we provide a machine learning (ML) method to predict the ionic conductivity for various ILs, where the dataset is composed of 5,700 data points for 414 ILs. Especially, all features of each IL are automatically extracted from the cations and anions by a graph neural network (GNN), which differs from the artificial feature selection in the previous work. Then we employ extreme gradient boosting (XGBoost), random forest (RF), decision tree (DT), and gradient boost regression tree (GBRT) to construct the ML models for predicting the ionic conductivity, demonstrating that all ML models utilizing the same GNN-based features accurately predict the ionic conductivity. Furthermore, we use the GNN+XGBoost model to perform a large-scale screening for 15,300 ILs created by pairing 180 cations with 85 anions under five different temperatures ranging from 275 to 325 K. Then we highlight 10 cations and 10 anions found in the top 5% ILs with high ionic conductivity from our predicted heat maps under all temperatures. Additionally, we compare the experimental and predicted temperature dependence of the ionic conductivity for five typical ILs, indicating the outstanding thermodynamic transferability of our GNN+ML models. Therefore, our GNN+ML framework proposed in this study presents a powerful tool for efficiently screening a wide range of IL properties, which offers experimental scientists a comprehensive road map to directionally design and synthesize high-performance ILs.

show abstract

Application of ionic liquid-clay nanocomposites on cotton fabric and determination of multi-functional properties

Altinisik Tagac,

Bozaci

2024

Cellulose

View full text Add to dashboard Cite

Machine learning assisted Structure-based models for predicting electrical conductivity of ionic liquids

Cited by 25 publications

References 60 publications

Experimental and DFT Studies on Electrochemical Performances of Ester-Containing Vinylimidazolium Ionic Liquids: Effect of the Ester Substituent and Anion

Experimental and DFT Studies on Electrochemical Performances of Ester-Containing Vinylimidazolium Ionic Liquids: Effect of the Ester Substituent and Anion

Large-Scale Screening for High Conductivity Ionic Liquids via Machine Learning Algorithm Utilizing Graph Neural Network-Based Features

Application of ionic liquid-clay nanocomposites on cotton fabric and determination of multi-functional properties

Contact Info

Product

Resources

About