The interest in green and sustainable solvents has been dramatically increasing in recent years because of the growing awareness of the impact of classical organic solvents on environmental pollution and human health. As a solution to these issues, several greener and more sustainable solvents have been proposed in recent years such as the novel Hydrophobic Eutectic Solvents (HESs). HESs have many advantageous characteristics and could be considered as a potential replacement for both ionic liquids and classical solvents. However, choosing the right HES with the required physiochemical properties for a certain application is an extremely difficult task, especially since large-scale experimental measurements are expensive and time-consuming. Thus, the development of predictive models capable of estimating the properties of these solvents could be considered as a powerful tool in screening new green and sustainable HESs. This work presents two novel Quantitative Structure–Property Relationship (QSPR) models for predicting the density and viscosity of HESs using Conductor-like Screening Model for Real Solvents (COSMO-RS) based descriptors. The data set used includes all the experimental measurements reported in the literature up to the date of writing this work to ensure that the developed models are highly reliable and robust. The results show that the proposed models were excellent at predicting the properties of HES not included in the training set as R² values of 0.9956 and 0.9871 were obtained for density and viscosity, respectively. This work presents an initiative towards the development of reliable models for predicting the properties of HESs as a means to promote an efficient solvent design approach that can aid in designing and simulating new processes utilizing these novel HESs.

Studies on deep eutectic solvents (DESs), a new class of "green" solvents, are attracting increasing attention from researchers, as evidenced by the rapidly growing number of publications in the literature. One of the main advantages of DESs is that they are tailor-made solvents, and therefore, the number of potential DESs is extremely large. It is essential to have computational methods capable of predicting the physicochemical properties of DESs, which are needed in many industrial applications and research. Surface tension is one of the most important properties required in many applications. In this work, we report a relatively generalized artificial neural network (ANN) for predicting the surface tension of DESs. The database used can be considered comprehensive because it contains 1571 data points from 133 different DES mixtures in 520 compositions prepared from 18 ions and 63 hydrogen bond donors in a temperature range of 277-425 K. The ANN model uses molecular parameter inputs derived from the conductor-like screening model for real solvents (S _σ-profiles). The training and testing results show that the best performing ANN architecture consisted of two hidden layers with 15 neurons each (9-15-15-1). The proposed ANN was excellent in predicting the surface tension of DESs, as R ² values of 0.986 and 0.977 were obtained for training and testing, respectively, with an overall average absolute relative deviation of 2.20%. The proposed models represent an initiative to promote the development of robust models capable of predicting the properties of DESs based only on molecular parameters, leading to savings in investigation time and resources.