(690b) Accelerating Discovery of Water Stable Metal-Organic Frameworks By Machine Learning

Metal-organic frameworks (MOFs) provide an extensive design landscape for nanoporous materials that drive innovation across energy and environmental fields. However, their practical applications are often hindered by water stability challenges. In this study, we propose a machine learning (ML) approach, trained on experimentally measured water stability, to accelerate the discovery of water-stable MOFs. We construct the largest database currently available that contains water stability information of synthesized MOFs, and categorize them according to their experimentally observed stability. Structural and chemical descriptors are featurized at various fragmental levels to develop ML classifiers for predicting water stability of MOFs. The ML classifiers achieve high prediction accuracy and demonstrate excellent transferability, effectively distinguishing the boundary between stability classes by leveraging structure-stability correlations. Finally, the predictions are validated by experimental tests. We anticipate our ML approach can serve as a prerequisite filtering tool to streamline the exploration of water-stable MOFs for important practical applications.