Machine learning enables interpretable discovery of innovative polymers for gas separation membranes

Polymer membranes perform innumerable separations with far-reaching environmental implications. Despite decades of research, 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 performance. Specifically, multitask ML models are trained on experimental data to link polymer chemistry to gas permeabilities of He, H-2, O-2, N-2, CO2, and CH4. We interpret the ML models and extract valuable insights into the contributions of different chemical moieties to permeability and selectivity. We then screen over 9 million hypothetical polymers and identify thousands that lie well above current performance upper bounds, including hundreds of never-before-seen ultrapermeable polymer membranes with O-2 and CO2 permeability greater than 10(4) and 10(5) Barrers, respectively. High-fidelity molecular dynamics simulations confirm the ML-predicted gas permeabilities of the promising candidates, which suggests that many can be translated to reality.

Automated summary

This study demonstrates a machine learning approach for discovering innovative polymers with ideal performance in membrane separation. By training multitask ML models with experimental data, the relationship between polymer chemistry and gas permeabilities is established. Thousands of potential polymers with significantly better performance than current upper bounds are identified, and molecular dynamics simulations confirm their predicted gas permeabilities.