The Open Catalyst Project is a collaborative research effort between Fundamental AI Research (FAIR) at META and the Department of Chemical Engineering at Carnegie Mellon University (CMU). It aims to use AI to build models and discover new catalysts for use in renewable energy storage to help address climate change.
Scalable and cost-effective solutions of renewable energy storage are essential to meet the world’s growing energy needs while mitigating climate change. As we increase our reliance on renewable energy sources like wind and solar, which produce power intermittently, storage is needed to transfer power from times of peak production to times of peak demand. This may require storing electricity for hours, days or months. One solution that offers the potential to scale nation-sized grids is to convert renewable energy into other fuels such as hydrogen. To be widely adopted, the process requires a cost-effective solution to driving the chemical reactions.
Finding low-cost catalysts to run these reactions at high rates is an open challenge. Through the use of quantum mechanical simulations (density functional theory), new catalyst structures can be tested and evaluated. Unfortunately, the high computational cost of these simulations limits the number of structures that can be tested. The use of AI or machine learning could provide a method to efficiently approximate these calculations, leading to new approaches in finding effective catalysts.
To enable the broader research community to participate in this important project, we have released the Open Catalyst 2020 (OC20) and 2022 (OC22) datasets for training ML models. These datasets contain 1.3 million molecular relaxations with the results of more than 260 million DFT calculations in total. In addition to the data, the baseline model and code are open-sourced on our Github page. Check out the leaderboard to see the latest results and submit yours to the evaluation server!