Prediction of Henry's law constants by matrix completion

Abstract

Methods for predicting Henry's law constants H ij are important as experimental data are scarce. We introduce a new machine learning approach for such predictions: matrix completion methods (MCMs) and demonstrate its applicability using a data base that contains experimental H ij values for 101 solutes i and 247 solvents j at 298 K. Data on H ij are only available for 2661 systems i + j. These H ij are stored in a 101 Â 247 matrix; the task of the MCM is to predict the missing entries. First, an entirely data-driven MCM is presented. Its predictive performance, evaluated using leave-one-out analysis, is similar to that of the Predictive Soave-Redlich-Kwong equation-of-state (PSRK-EoS), which, however, cannot be applied to all studied systems. Furthermore, a hybrid of MCM and PSRK-EoS is developed in a Bayesian framework, which yields an unprecedented performance for the prediction of H ij of the studied data set.

Database for liquid phase diffusion coefficients at infinite dilution at 298 K and matrix completion methods for their prediction

“…Both the form of the prior and the likelihood, including the scale parameter λ , are hyperparameters of the model. In preliminary studies with different configurations, the hyperparameter set from our previous work 31 proved to be most suitable, which was therefore adopted here. All feature vectors are of length K , where K is the number of features considered for each solute and each solvent.…”

“…Specifically, the means of the respective preliminary features were adopted, whereas the standard deviations of the features were scaled with a constant factor, such that the mean of all resulting standard deviations was σ = 0.5. This scaling procedure was carried out analogously to our previous work 31 and ensures that the model remains flexible enough to reasonably consider the experimental training data. The final informative prior for the maturation step of the hybrid MCM was then obtained by multiplying the scaled posterior from the distillation step with the uninformed prior distribution as used in the data-driven MCM.…”

“…4,17 In particular, they have been applied very successfully for predicting activity coefficients and Henry's law constants. 4,[28][29][30][31] In the present work, we extend the MCM approach to the prediction of diffusion coefficients.…”

Prediction of parameters of group contribution models of mixtures by matrix completion

“…In a series of recent papers, we have demonstrated the capabilities of MCMs for predicting different types of thermodynamic data of mixtures using various component-based approaches. [22][23][24][25][26][27] However, these component-based approaches are inherently limited regarding the number of components that are covered; the respective models complete a matrix spanned by the components that are part of the mixtures in the training set. This is not the case for the group contribution methods, which we consider in the present work: as the groups form building blocks from which components can be created flexibly, the scope of the group contribution methods for mixture properties is inherently extremely large -and it can now be extended substantially by using an MCM to complete the set of group-interaction parameters.…”

A Transformer-Convolutional Neural Network Based Framework for Predicting Ionic Liquid Properties

“…42 The γ ∞ prediction accuracy of this model exceeds all ML models that use manually designed fingerprints. However, due to the matrix completion essence of the selected method, 43 the developed RS model mainly applies to already covered ILs and solutes in the database.…”