Associate Professor Seonah Kim in the department of chemistry, has received a National Science Foundation (NSF) award to develop solubility databases and neural network models from the Chemical Theory, Models, and Computational Methods (CTMC) program in the NSF Division of Chemistry. The three-year, approximately $449,440 grant will allow Kim’s group to design chemical processes with multicomponent solvents through self-evolving solubility databases and neural networks. By using novel data augmentation techniques, the Kim group will develop self-evolving databases which can reconcile differences between experimental and computational data. The graph neural networks (GNNs) from this work will be applied to unknown solvents as well as unknown polymers, yielding robust and experimentally verified ML models to predict solubility over a broad swath of chemical space.