Prediction of Henry's law constants by matrix completion

Abstract

AbstractMethods for predicting Henry's law constants Hij 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 Hij values for 101 solutes i and 247 solvents j at 298 K. Data on Hij are only available for 2661 systems i + j. These Hij are stored in a 101 × 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 Hij of the studied data set.