Design of Supported Ionic Liquid Membranes for CO₂ Capture Using a Generative AI-Based Approach

Area of Science:

• Materials Science
• Chemical Engineering
• Artificial Intelligence

Background:

• Climate change necessitates efficient carbon capture technologies.
• Traditional material design for CO2 capture is slow and expensive.
• Supported ionic liquid membranes (SILMs) show promise for CO2 capture.

Purpose of the Study:

• To apply generative AI, specifically a conditional variational autoencoder (CVAE), to accelerate the design of SILMs for CO2 capture.
• To reduce the time and cost associated with experimental material discovery.

Main Methods:

• A CVAE model was trained on a limited experimental dataset of SILMs.
• The CVAE generated and predicted numerous synthetic SILM candidates.
• Promising SILMs were synthesized and experimentally evaluated for CO2 capture capacity.

Main Results:

• The CVAE model successfully generated a large number of SILM candidates.
• Experimental evaluation showed strong predictive accuracy, with close agreement between predicted and measured CO2 capture values.
• The AI-driven approach significantly reduced the need for extensive trial-and-error experiments.

Conclusions:

• Generative AI, particularly CVAE, is a powerful tool for accelerating materials discovery in carbon capture.
• This AI-driven methodology offers a cost-effective and efficient pathway to explore vast design spaces for advanced materials.
• The study demonstrates the potential to revolutionize the development of materials for enhanced CO2 capture.