Perspective: Machine Learning of Thermophysical Properties

In this first contribution to Fluid Phase Equilibria’s Perspective Series, we discuss the role of machine learning (ML) in research on thermophysical properties. Following idea behind new series, is no classical review aiming at a comprehensive coverage previous work field. Instead, provide an overview developments and point out promising directions field, linking perspectives chemical engineers computer scientists. The topics cover include data properties; long history ML methods which, however, stemmed so far almost exclusively from supervised learning; other interest; as well important subject how merge physical modeling with create hybrid approaches, which expect play central future. discussion illustrated by examples application matrix completion for prediction mixture properties, have recently introduced.