(169b) Data Set and Data-Driven Models for Predicting Metal-Organic Framework Stability in Water and Harsh Environments

Metal-organic frameworks (MOFs) are porous materials with applications in gas separations and catalysis, but a lack of water stability often limits their practical use given the ubiquity of water in air and the environment. Consequently, it is necessary to predict whether a MOF is water-stable before investing time and resources into synthesis. While heuristics for designing water-stable MOFs such as hard-soft acid-base theory are well-known, these can lack generality and artificially limit the diversity of explored chemistry due to narrowly defined criteria. Thus, we instead use machine learning (ML) models trained on experimental MOF stability data to improve generality and utilize examples spanning MOF chemical space. In an improvement on previous ML efforts, we enlarge the available training data for MOF water stability prediction by over 400%, adding 911 MOFs with water stability labels assigned through manuscript analysis. The additional data is shown to improve ML model performance (test ROC-AUC > 0.8) over diverse chemistry for the prediction of both water stability and stability in harsher acidic conditions. We illustrate how the expanded data set and models can be used with previously developed activation stability models to run genetic algorithms that quickly screen ~10,000 MOFs to identify candidates with multivariate stability (i.e., for activation, in water, and in acid). Model analysis and genetic algorithm results uncover metal and geometry-specific design rules for synthesizing robust MOFs. The data set and ML models developed in this work, which we disseminate through an easy-to-use web interface, are expected to contribute toward the accelerated discovery of novel, water-stable MOFs for applications requiring water stability such as direct air gas capture and water treatment.