Although computational models have been used to predict adsorption of molecules in large libraries of porous adsorbents, previous work of this kind has focused on a small number of molecules as potential adsorbates. In this study, molecular simulations were used to consider the adsorption of a diverse range of molecules in a large collection of metal-organic framework (MOF) materials. Specifically, 11 304 isotherms were obtained from molecular simulations of 24 different adsorbates in 471 MOFs. This information provides insight into several interesting questions that could not be addressed with previously available data. Highly computationally efficient methods are introduced that can predict isotherms for a wide range of adsorbing molecules with far less computation than traditional molecular simulations. By characterizing the 276 binary mixtures defined by the molecules considered, "privileged" adsorbents are shown to exist, which are effective for separating many different molecular mixtures. Finally, correlations that were developed previously to predict molecular solubility in polymers are found to be surprisingly effective in predicting the average properties of molecules adsorbing in MOFs.

Adsorptive hydrogen storage is a desirable technology for fuel cell vehicles, and efficiently identifying the optimal storage temperature requires modeling hydrogen loading as a continuous function of pressure and temperature. Using data obtained from high-throughput Monte Carlo simulations for zeolites, metal-organic frameworks, and hyper–cross-linked polymers, we develop a meta-learning model that jointly predicts the adsorption loading for multiple materials over wide ranges of pressure and temperature. Meta-learning gives higher accuracy and improved generalization compared to fitting a model separately to each material and allows us to identify the optimal hydrogen storage temperature with the highest working capacity for a given pressure difference. Materials with high optimal temperatures are found in close proximity in the fingerprint space and exhibit high isosteric heats of adsorption. Our method and results provide new guidelines toward the design of hydrogen storage materials and a new route to incorporate machine learning into high-throughput materials discovery.

Industrial separations of near-azeotropic chemicals, species with very similar boiling points, are energy-and capital-intensive. Adsorption-based processes can energy-efficiently separate near-azeotropic mixtures provided suitable adsorbent materials can be found. Among the full diversity of industry-relevant molecules, millions of these mixtures exist, meaning that discovery of mixture-specific adsorbents by direct experiment is infeasible. We show that vast numbers of adsorbents and adsorbing molecules can be explored in a powerful way by coupling atomistic simulations with machine learning. This concept is demonstrated by describing the adsorption of ∼54 000 industry-relevant chemicals in an experimentally derived set of thousands of metal−organic framework materials. Our results identify thousands of near-azeotropic mixtures that can be efficiently separated using adsorption and open possibilities for creating adsorption processes for complex mixtures with many components.

Adsorption-based separations using metal–organic frameworks (MOFs) are a promising alternative to traditional energy-intensive separation process. Machine learning (ML) methods have been applied to predict large collections of adsorption isotherms in MOFs. Previous ML models, however, focus only on predicting single-component adsorption isotherms of a small number of molecules at a single temperature and lack accuracy in the dilute limit. Here we describe a useful strategy for predicting Henry’s constants and heats of adsorption for a diverse set of molecules in large collections of MOFs. To achieve this, a data set containing 21,195 MOF–molecule pairs with 45 adsorbates in 471 MOFs is generated, and a set of 135 descriptors combining energy and chemical information is developed. Robust ML models are developed to predict Henry’s constants and heats of adsorption after removing physically unfavorable adsorption pairs. The adsorption selectivity of near-azeotropic mixtures at two temperatures (300 and 373 K) is predicted with acceptable accuracy by using the predicted Henry’s constants and heats of adsorption. The ability to make temperature-dependent predictions is important for many practical separation applications. Our work sheds light on important challenges and opportunities for developing accurate models predicting adsorption properties for diverse collection of adsorbates and adsorbents.

Quantitatively modeling adsorbate diffusion through zeolitic imidazolate frameworks (ZIFs) must account for the inherent flexibility of these materials. The lack of a transferable intramolecular ZIF force field (FF) for use in classical simulations has previously made an accurate simulation of adsorbate diffusion in many ZIFs impossible. We resolve this problem by introducing a density functional theory parameterized force field (FF) for ZIFs named the intraZIF-FF, which includes perturbations to the class I force fields previously used to model ZIFs. This FF outperforms ad hoc force fields at predicting ab initio relative energies and atomic forces taken from fully periodic ab initio molecular dynamics simulations of SALEM-2, ZIF-7, ZIF-8, and ZIF-90. We use the intraZIF-FF to predict the infinite dilution self-diffusion coefficients of 30 adsorbates with molecular diameters ranging from 2.66 to 7.0 Å in these 4 ZIFs. These results greatly increase the number of adsorbates for which accurate information about molecular diffusion in ZIFs is available.