Discovery of Innovative Polymers for Next-Generation Gas-Separation Membranes using Interpretable Machine Learning

Polymer membranes perform innumerable separations with far-reaching environmental implications. Despite decades of research on membrane technologies, design of new membrane materials remains a largely Edisonian process. To address this shortcoming, we demonstrate a generalizable, accurate machine-learning (ML) implementation for the discovery of innovative polymers with ideal separation performance. Specifically, multitask ML models are trained on available experimental data to link polymer chemistry to gas permeabilities of He, H2, O2, N2, CO2, and CH4. We interpret the ML models and extract chemical heuristics for membrane design, through Shapley Additive exPlanations (SHAP) analysis. We then screen over nine million hypothetical polymers through our models and identify thousands of candidates that lie well above current performance upper bounds. Notably, we discover hundreds of never-before-seen ultrapermeable polymer membranes with O2 and CO2 permeability greater than 104 and 105 Barrer, respectively. These hypothetical polymers are capable of overcoming undesirable trade-off relationship between permeability and selectivity, thus significantly expanding the currently limited library of polymer membranes for highly efficient gas separations. High-fidelity molecular dynamics simulations confirm the ML-predicted gas permeabilities of the promising candidates, which suggests that many can be translated to reality.

Discovery of Innovative Polymers for Next-Generation Gas-Separation Membranes using Interpretable Machine Learning

Polymer membranes perform innumerable separations with far-reaching environmental implications. Despite decades of research on membrane technologies, design of new membrane materials remains a largely Edisonian process. To address this shortcoming, we demonstrate a generalizable, accurate machine-learning (ML) implementation for the discovery of innovative polymers with ideal separation performance. Specifically, multitask ML models are trained on available experimental data to link polymer chemistry to gas permeabilities of He, H2, O2, N2, CO2, and CH4. We interpret the ML models and extract chemical heuristics for membrane design, through Shapley Additive exPlanations (SHAP) analysis. We then screen over nine million hypothetical polymers through our models and identify thousands of candidates that lie well above current performance upper bounds. Notably, we discover hundreds of never-before-seen ultrapermeable polymer membranes with O2 and CO2 permeability greater than 104 and 105 Barrer, respectively, orders of magnitude higher than currently available polymeric membranes. These hypothetical polymers are capable of overcoming undesirable trade-off relationship between permeability and selectivity, thus significantly expanding the currently limited library of polymer membranes for highly efficient gas separations. High-fidelity molecular dynamics simulations confirm the ML-predicted gas permeabilities of the promising candidates, which suggests that many can be translated to reality.

Mixed Matrix Membranes Based on Torlon® and ZIF-8 for High-Temperature, Size-Selective Gas Separations

Torlon® is a thermally and plasticization-resistant polyamide imide characterized by low gas permeability at room temperature. In this work, we aimed at improving the polymer performance in the thermally-enhanced He/CO2 and H2/CO2 separations, by compounding Torlon® with a highly permeable filler, ZIF-8, to fabricate Mixed Matrix Membranes (MMMs). The effect of filler loading, gas size, and temperature on the MMMs permeability, diffusivity, and selectivity was investigated. The He permeability increased by a factor of 3, while the He/CO2 selectivity decreased by a factor of 2, when adding 25 wt % of ZIF-8 at 65 °C to Torlon®; similar trends were observed for the case of H2. The MMMs permeability and size-selectivity were both enhanced by temperature. The behavior of MMMs is intermediate between the pure polymer and pure filler ones, and can be described with models for composites, indicating that such materials have a good polymer/filler adhesion and their performance could be tailored by acting on the formulation. The behavior observed is in line with previous investigations on MMMs based on glassy polymers and ZIF-8, in similar conditions, and indicates that ZIF-8 can be used as a polymer additive when the permeability is a controlling aspect, with a proper choice of loading and operative temperature.

Computation-informed optimization of Ni(PyC)₂ functionalization for noble gas separations

Metal-organic frameworks (MOFs) are promising nanoporous materials for the adsorptive capture and separation of noble gases at room temperature. Among the numerous MOFs synthesized and tested for noble gas separations, Ni(PyC)₂ (PyC = pyridine-4-carboxylate) exhibits one of the highest xenon/krypton selectivities at room temperature. Like lead-optimization in drug discovery, here we aim to tune the chemistry of Ni(PyC)₂, by appending a functional group to its PyC ligands, to maximize its Xe/Kr selectivity. To guide experiments in the laboratory, we virtually screen Ni(PyC-X)₂ (X=functional group) structures for noble gas separations by (i) constructing a library of Ni(PyC-X)₂ crystal structure models then (ii) using molecular simulations to predict noble gas (Xe, Kr, Ar) adsorption and selectivity at room temperature in each structure. The virtual screening predicts several Ni(PyC-X)₂ structures to exhibit a higher Xe/Kr, Xe/Ar, and Kr/Ar selectivity than the parent Ni(PyC)₂ MOF, with Ni(PyC-m-NH₂)₂ among them. In the laboratory, we synthesize Ni(PyC-m-NH₂)₂, determine its crystal structure by X-ray powder diffraction, and measure its Xe, Kr, and Ar adsorption isotherms (298 K). In agreement with our molecular simulations, the Xe/Kr, Xe/Ar, and Kr/Ar selectivities of Ni(PyC-m-NH₂)₂ exceed those of the parent Ni(PyC)₂. Particularly, Ni(PyC-m-NH₂)₂ exhibits a [derived from experimental, equilibrium adsorption isotherms] Xe/Kr selectivity of 20 at dilute conditions and 298 K, compared to 17 for Ni(PyC)₂. According to in situ X-ray diffraction, corroborated by molecular models, Ni(PyC-m-NH₂)₂ presents well-defined binding pockets tailored for Xe and organized along its one-dimensional channels. In addition to discovering the new, performant Ni(PyC-m-NH₂)₂ MOF for noble gas separations, our study illustrates the computation-informed optimization of the chemistry of a "lead" MOF to target adsorption of a specific gas.

Glassy Polymers—Diffusion, Sorption, Ageing and Applications

For the past few decades, researchers have been intrigued by glassy polymers, which have applications ranging from gas separations to corrosion protection to drug delivery systems. The techniques employed to examine the sorption and diffusion of small molecules in glassy polymers are the subject of this review. Diffusion models in glassy polymers are regulated by Fickian and non-Fickian diffusion, with non-Fickian diffusion being more prevalent. The characteristics of glassy polymers are determined by sorption isotherms, and different models have been proposed in the literature to explain sorption in glassy polymers over the last few years. This review also includes the applications of glassy polymers. Despite having many applications, current researchers still have difficulty in implementing coating challenges due to issues such as physical ageing, brittleness, etc., which are briefly discussed in the review.