American scientists from Argonne National Laboratory in Illinois have significantly accelerated the creation of a material that will absorb carbon emissions using a tool based on artificial intelligence (AI). The study was published in the scientific journal magazine Nature Contact Chemistry (NCC).
Carbon capture remains a critical technology for reducing greenhouse gas emissions from power plants and other industrial facilities to combat climate change. However, a material suitable for efficient carbon capture at low cost has not yet been found. One option is metal-organic frameworks (MOFs), which can selectively capture carbon dioxide particles due to their porous structure.
There are three types of building blocks in MOF molecules: inorganic units, organic units, and organic linkers. They can be placed in a variety of positions and configurations, challenging scientists to develop and test numerous potential MOFs.
Using a specially trained generative AI model, the team was able to rank more than 120 thousand possible IOC options in just 30 minutes.
According to the researchers, AI tools will help scientists solve the problem of creating effective MOFs, which humans have been unable to tackle for more than 20 years since the discovery of this class of materials.
Previously AI helped Scientists are discovering unknown properties of proteins.