Making thermodynamic models of mixtures predictive by machine learning: matrix completion of pair interactions
Fabian Jirasek, Robert Bamler, Sophie Fellenz, Michael Bortz, Marius Kloft, Stephan Mandt, Hans Hasse
Abstract
set of UNIQUAC parameters for all binary systems of these components, which allows us to predict, in principle, activity coefficients at arbitrary temperature and composition for any combination of these components, not only for binary but also for multicomponent systems. The hybrid model even outperforms the best available physical model for predicting activity coefficients, the modified UNIFAC (Dortmund) model.
Topics & Concepts
Matrix completionMatrix (chemical analysis)Computer scienceMachine learningArtificial intelligenceChemistryComputational chemistryChromatographyGaussianPhase Equilibria and ThermodynamicsAdvanced Thermodynamics and Statistical MechanicsThermodynamic properties of mixtures