The database was built using machine learning models and nearly 40 million quantum mechanics calculations, making it the most robust of its kind. The researchers were able to identify about 241 metal-organic frameworks (MOFs) with high potential for direct air capture. The entire OpenDAC dataset project is open source, and the team hopes that the scientific community will join the search for suitable materials. The research was published in ACS Central Science, a journal of the American Chemical Society.
Key takeaways:
- Georgia Tech and Meta have collaborated to create a massive open-source database, named OpenDAC, to aid in the design and implementation of direct air capture technologies, a potential solution to excessive carbon emissions.
- The database, which contains reaction data for 8,400 different materials, was used to train an AI model that is significantly faster than existing chemistry simulations.
- The researchers identified about 241 metal-organic frameworks (MOFs) with high potential for direct air capture. MOFs are a class of materials known for their ability to attract and trap carbon dioxide.
- The entire OpenDAC dataset project is open source, and the researchers hope the scientific community will join the search for suitable materials for carbon capture.