Graph neural networks for temperature-dependent activity coefficient prediction of solutes in ionic liquids. (March 2023)

• Record Type: Journal Article
• Authors: Rittig, Jan G.; Ben Hicham, Karim; Schweidtmann, Artur M.; Dahmen, Manuel; Mitsos, Alexander
• Is Part Of: Computers & chemical engineering. Volume 171(2023)
• Publication Date: 2023-03
• Subjects: Graph learning -- Machine learning -- Green solvents -- Activity coefficient prediction -- Ionic liquids; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2023.108153
• Languages: English
• ISSNs: 0098-1354

Abstract

Abstract: Ionic liquids (ILs) are important solvents for sustainable processes and predicting activity coefficients (ACs) of solutes in ILs is needed. Recently, matrix completion methods (MCMs), transformers, and graph neural networks (GNNs) have shown high accuracy in predicting ACs of binary mixtures, superior to well-established models, e.g., COSMO-RS and UNIFAC. GNNs are particularly promising here as they learn a molecular graph-to-property relationship without pretraining, typically required for transformers, and are, unlike MCMs, applicable to molecules not included in training. For ILs, however, GNN applications are currently missing. Herein, we present a GNN to predict temperature-dependent infinite dilution ACs of solutes in ILs. We train the GNN on a database including more than 40, 000 AC values and compare it to a state-of-the-art MCM. The GNN and MCM achieve similar high prediction performance, with the GNN additionally enabling high-quality predictions for ACs of solutions that contain ILs and solutes not considered during training. Highlights: Graph neural networks for activity coefficient prediction of solutes in ionic liquids. Fast prediction of temperature-dependent infinite dilution activity coefficients. Comparative prediction quality to state-of-the-art matrix completion methods. Successful generalization to previously unseen ionic liquid and solute molecules.