Published: April 23, 2024

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 air environment. Consequently, it is useful to predict whether MOF water-stable before investing time resources into synthesis. Existing heuristics for designing MOFs generality artificially limit diversity explored chemistry due narrowly defined criteria. Machine learning (ML) models offer promise improve predictions require diverse experimental data be trained. In an improvement on previous efforts, we enlarge available training prediction by over 400%, adding 911 labels assigned through semi-automated manuscript analysis curate new set WS24. The additional shown ML model performance (test ROC-AUC > 0.8) both harsher acidic conditions. We illustrate how expanded can used previously developed activation carry out genetic algorithms quickly screen ~10,000 from space hundreds thousands candidates multivariate (i.e., activation, water, acid). Model algorithm results uncover metal- geometry-specific design rules robust MOFs. this work, which disseminate easy-to-use web interface, expected contribute toward accelerated discovery novel, such as direct capture treatment.

Language: Английский