Researchers Try To Find New Carbon Capture Materials Using The Power Of AI

Researchers Try To Find New Carbon Capture Materials Using The Power Of AI - Carbon Herald
Credit: Gerd Altmann | Pixabay

Finding new materials that capture CO2 is a critical part of the acceleration of the carbon capture and direct air capture industries. To increase the speed of discovery of new carbon capture absorbers, researchers at University of Illinois Chicago, Argonne National Laboratory and several other institutions are collaborating to harness the power of generative AI. 

Generative AI uses deep-learning models that can take raw data and “learn” to generate statistically probable outputs when prompted. The results of the research are published in a paper: A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture.

Relevant: Study Finds Materials Best Suited For Emerging Carbon Capture Tech

“The race for capturing carbon hinges on finding needles in a haystack, and trial and error is too slow. You have billions and billions of possibilities, and then you must narrow down to candidates that are good carbon absorbers… With this project, we have taken the first significant step towards closing that gap by using generative AI,” explained Santanu Chaudhuri, professor of civil, materials and environmental engineering at UIC and director of manufacturing science and engineering at Argonne. 

Photo by Sharon McCutcheon on Unsplash

The AI model created by the research team explores the vast space of chemical arrangements that could be used to create materials such as metal-organic frameworks that capture carbon dioxide. After the model explored the billions of possibilities, it assembled 120,000 potential structures. 

The team then had the task to run additional tests to remove those materials with improbable physical or chemical features or such that are too difficult or expensive to make. They had to use computer models to predict each structure’s carbon capture abilities. Then, they subjected the best 364 candidates to in-depth, 3D molecular dynamics simulations of their structural qualities.

Relevant: NIST Scientists Out To Discover New Direct Air Capture Materials

At the end, the researchers selected six structures that are the highest-performing. They can be synthesized in laboratories and subjected to real-world experiments, while the data from the computational tests can be fed back into the AI model to produce another generation of even higher-quality candidates.

According to the paper, the entire framework, from AI model to 3D simulations, can be completed in 12 hours using modern supercomputers. 

“We want to release the power and the imagination of a large community of different researchers because carbon capture is an urgent need… If you keep it to yourself, then you are reducing the chance of innovation,” added Mr Chaudhuri.

Leave a Reply

Your email address will not be published. Required fields are marked *

Related Posts
Total
0
Share