Database and new models based on a group contribution method to predict the refractive index of ionic liquids

Insights into modeling refractive index of ionic liquids using chemical structure-based machine learning methods

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.

Physicochemical Characterization and Simulation of the Solid-Liquid Equilibrium Phase Diagram of Terpene-Based Eutectic Solvent Systems

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 e_r 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.