SurfPro – a curated database and predictive model of experimental properties of surfactants
Stefan Hödl, Luc Hermans, Pim Dankloff, Aigars Piruska, Wilhelm T. S. Huck, William E. Robinson
Abstract
SurfPro is a database of 1624 surfactants and their experimental properties. To address missing property values in this database, graph neural network ensembles were trained for multi-property prediction to impute values for all missing properties.
Topics & Concepts
DatabaseComputer scienceMaterial Properties and Processing