Molecular-based artificial neural network for predicting the electrical conductivity of deep eutectic solvents

Accurate prediction of carbon dioxide capture by deep eutectic solvents using quantum chemistry and a neural network

“…Lemaoui et al extensively used the COSMO-RS calculated Sigma profile areas as an input parameter for developing QSPR models for predicting the thermodynamic properties (density, viscosity, surface tension, electrical conductivity, and pH) of DESs. [36][37][38] In addition, Nordness et al (2021) have developed a machine learning model for predicting thermophysical properties of ionic liquids using the Sigma profiles. 39 Therefore, the COSMO-RS derived Sigma profile parameters might also be explored for establishing a machine learning model for CO 2 solubility prediction in DESs.…”

Multitask Neural Network for Mapping the Glass Transition and Melting Temperature Space of Homo- and Co-Polyhydroxyalkanoates Using σProfiles Molecular Inputs

“…107 Furthermore, as was aforementioned, each σ Profiles is composed of 51 points, which represent the σ Profiles values at 51 different σ values, where it has been successfully included as a molecular descriptor in our previous works for predicting deep eutectic solvents and ionic liquids. 89,90 Abranches et al 108 also used the σ Profiles of 1432 molecular solvents as molecular descriptors in ML to develop ANNs that reliably predict a wide variety of physical and chemical properties including molar mass, boiling temperature, vapor pressure, density, refractive index, and solubility.…”

“…Nevertheless, there is no defined method to select the ideal network architecture and determine the number of hidden layers and the number of neurons in each hidden layer. For instance, previous studies used either one or two hidden layers , for predicting the properties of deep eutectic solvents. Thus, the most prevalent approach in the literature is trial and error .…”

Critical Properties of Ternary Deep Eutectic Solvents Using Group Contribution with Extended Lee–Kesler Mixing Rules

“…As such, computational tools are essential for narrowing down the feasible combinations of DESs, as experimental investigations can be expensive and time-consuming. Thermodynamic models such as COSMO-RS can be useful tools for predicting the physicochemical properties of DESs and ILs. − These models can provide insights into the molecular-level interactions between the components and aid in the selection and design of appropriate solvent systems for specific applications. Additionally, the UNIFAC-Lei model has been widely employed in the prediction of the phase equilibrium of ILs. , …”

“…The physical, physicochemical, and transport properties of DESs, such as boiling point, density, viscosity, surface tension, pH, vapor pressure, etc., are primarily determined by the interaction and structure of the DES’s constituents. Such properties can be tailored by modifying the HBA and HBD structure and their corresponding molar ratios. , Like any solvent, the physicochemical properties of DESs play a pivotal role in the feasibility and applicability of a specific chemical or physical process. − For example, the density of a solvent is of great importance in the separation between the aqueous and organic phases for hydrophobic DESs, , and the efficiency of solid–liquid extraction processes ( e.g ., sugar extraction). Likewise, the viscosity of a solvent affects the mass transfer from and to the solvent. , For a balanced process operation and design, careful choice of the DES and its constituent should be considered .…”