AI screens 100,000+ membrane combinations, predicting carbon capture performance within seconds
Reducing carbon dioxide emissions from industrial processes and energy production remains one of the major technological challenges in addressing climate change. Membrane-based gas separation offers an energy-efficient alternative to conventional separation technologies, but identifying membranes that allow gases to pass through rapidly while also separating them effectively has long presented a…
Researchers at Koç University have developed a machine-learning framework to expedite the discovery of high-performance membrane materials for carbon capture. The system evaluated over 100,000 combinations of metal-organic frameworks (MOFs) and polymers, predicting membrane performance within seconds. Membrane-based gas separation is a promising energy-efficient alternative to conventional technologies, but designing effective membranes remains challenging.
By embedding MOFs within polymer membranes, the researchers aimed to combine the scalability of polymers with the selective gas transport of MOFs. They paired 8,683 MOFs with 12 polymers, creating a dataset of 104,196 potential combinations. Molecular simulations were used to calculate the interaction of gases with MOFs, which were then used to train machine-learning models.
The most accurate model used a two-step strategy, first predicting the gas permeability of the MOF and then estimating the mixed-matrix membrane performance based on the polymer properties. The framework identified many promising MOF-polymer combinations that could surpass the permeability and selectivity limits of conventional polymer membranes.
The approach provides practical guidance on optimizing MOF characteristics within polymers and serves as a rapid screening tool for researchers to prioritize promising materials for further experimental testing.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
