Machine Learning for Polymer Design to Enhance Pervaporation-Based Organic Recovery.

Pervaporation (PV) is an effective membrane separation process for organic dehydration, recovery, and upgrading. However, it is crucial to improve membrane materials beyond the current permeability-selectivity trade-off. In this research, we introduce machine learning (ML) models to identify high-potential polymers, greatly improving the efficiency and reducing cost compared to conventional trial-and-error approach. We utilized the largest PV data set to date and incorporated polymer fingerprints and features, including membrane structure, operating conditions, and solute properties. Dimensionality reduction, missing data treatment, seed randomness, and data leakage management were employed to ensure model robustness. The optimized LightGBM models achieved RMSE of 0.447 and 0.360 for separation factor and total flux, respectively (logarithmic scale). Screening approximately 1 million hypothetical polymers with ML models resulted in identifying polymers with a predicted permeation separation index >30 and synthetic accessibility score <3.7 for acetic acid extraction. This study demonstrates the promise of ML to accelerate tailored membrane designs.

Tough and Recyclable Phase-Separated Supramolecular Gels via a Dehydration-Hydration Cycle.

Hydrogels are compelling materials for emerging applications including soft robotics and autonomous sensing. Mechanical stability over an extensive range of environmental conditions and considerations of sustainability, both environmentally benign processing and end-of-life use, are enduring challenges. To make progress on these challenges, we designed a dehydration-hydration approach to transform soft and weak hydrogels into tough and recyclable supramolecular phase-separated gels (PSGs) using water as the only solvent. The dehydration-hydration approach led to phase separation and the formation of domains consisting of strong polymer-polymer interactions that are critical for forming PSGs. The phase-separated segments acted as robust, physical cross-links to strengthen PSGs, which exhibited enhanced toughness and stretchability in its fully swollen state. PSGs are not prone to overswelling or severe shrinkage in wet conditions and show environmental tolerance in harsh conditions, e.g., solutions with pH between 1 and 14. Finally, we demonstrate the use of PSGs as strain sensors in air and aqueous environments.