Predicting and screening high-performance polyimide membranes using negative correlation based deep ensemble methods

Polyimide polymer membranes have become critical materials in gas separation and storage applications due to their high selectivity and excellent permeability. However, with over 107 known types of polyimides, relying solely on experimental research means potential high-performance candidates are likely to be overlooked. This study employs a deep learning method optimized by negative correlation ensemble techniques to predict the gas permeability and selectivity of polyimide structures, enabling rapid and efficient material screening. We propose a deep neural network model based on negative correlation deep ensemble methods (DNN-NCL), using Morgan molecular fingerprints as input. The DNN-NCL model achieves an R2 value of approximately 0.95 on the test set, which is a 4% improvement over recent model performance, and effectively mitigates overfitting with a maximum discrepancy of less than 0.03 between the training and test sets. High-throughput screening of over 8 million hypothetical polymers identified hundreds of promising candidates for gas separation membranes, with 14 structures exceeding the Robeson upper bound for CO2/N2 separation. Visualization of high-throughput predictions shows that although the Robeson upper bound was never explicitly used as a model constraint, the majority of predictions are compressed below this limit, demonstrating the deep learning model's ability to reflect real-world physical conditions. Reverse analysis of model predictions using SHAP analysis achieved interpretability of the deep learning model's predictions and identified three key functional groups deemed important by the deep neural network for gas permeability: carbonyl, thiophene, and ester groups. This established a bridge between the structure and properties of polyimide materials. Additionally, we confirmed that two polyimide structures predicted by the model to have excellent CO2/N2 selectivity, namely 6-methylpyrimidin-5-amine and 1,4,5,6-tetrahydropyrimidin-2-amine, have been experimentally validated in previous studies. This research demonstrates the feasibility of using deep learning methods to explore the vast chemical space of polyimides, providing a powerful tool for discovering high-performance gas separation membranes.

Unprecedented toughening high-performance polyhexahydrotriazines constructed by incorporating point-face cation-π interactions in covalently crosslinked networks and the visual detection of tensile strength

We described a new concept for the design of high-performance supramolecular thermosets by incorporating point-face cation-π interactions in covalently crosslinked networks. Our findings showed an unprecedented increase in tensile strength and extensibility at once, a previously unknown behavior for stiff high performance polymers.

Cation-π induced lithium-doped conjugated microporous polymer with remarkable hydrogen storage performance

A cation-π induced lithium-doped conjugated microporous polymer, Li+-PTAT, was constructed. It was proved that the point to face cation-π interactions between Li+ and indole can endow the resulting Li+-PTAT with high Li+ content and without agglomeration, which further leads to its encouraging hydrogen storage capacity.

A recyclable indole-based polymer for trinitrotoluene adsorption via the synergistic effect of dipole–π and donor–acceptor interactions

A new type of indole-based porous organic polymer with amine units (PAIN) has been constructed, which possesses encouraging and effective adsorption properties for trinitrotoluene by taking advantage of the synergistic effect of dipole–π and donor–acceptor interactions.

Cost-effective preparation of microporous polymers from formamide derivatives and adsorption of CO2 under dry and humid conditions

Nitrogen-rich microporous polymers are prepared via a catalyst-free polymerization reaction using formamide derivatives as monomers, which exhibit outstandingly high CO₂/N₂ selectivity up to 151 and 173 at 273 K under dry and humid conditions, respectively.

Post-modified porphyrin imine gels with improved chemical stability and efficient heterogeneous activity in CO2 transformation

Gel catalysts have been developed based on dynamic covalent chemistry and post-modification methods for improved chemical stability and catalytic activity.

Microporous organic polymer-induced gel electrolytes for enhanced operation stability of electrochromic devices

Gel electrolytes were synthesized by the formation of microporous organic polymers in the presence of LiClO₄ and NMP, showing enhanced operation stability of electrochromic cells, compared with liquid electrolytes.