(Subscribe to our Today's Cache newsletter for a quick snapshot of top 5 tech stories. Click here to subscribe for free.)
Facebook and Carnegie Mellon University have launched a dataset, called Open Catalyst Project, to discover low-cost catalysts that can help increase storing efficiency of renewable energy. They are also asking the scientific community to contribute to their effort in finding new, efficient ways of storing renewable energy.
The duo intend to use artificial intelligence (AI) to accelerate quantum mechanical simulations by 1,000x in order to discover new electrocatalysts needed for more efficient and scalable ways to store and use renewable energy, Facebook said in a statement.
ADVERTISEMENT
Renewables made up for 26.2% of global electricity generation in 2018, and that is expected to rise to 45% by 2040, according to estimates from Center for Climate and Energy Solutions.
One of the few scalable solutions entails converting excess solar and wind energy into other fuels, such as hydrogen or ethanol. Unfortunately, current methods for doing so are inefficient or rely on rare and expensive electrocatalysts like platinum, limiting their practicality. The Open Catalyst Project's goal is to discover low-cost catalysts to drive these chemical reactions.
Also read |
ADVERTISEMENT
ADVERTISEMENT
To achieve this, the team will use AI to accurately predict atomic interactions dramatically faster than the compute-heavy simulations scientists rely on today. Calculations that take modern laboratories days could, with the help of AI, take seconds. This has ramifications outside catalysis, and will enable scientists to rapidly explore and iterate on other challenges that involve quantum mechanics, Facebook said.
The California-based company said it will make its baseline model available on GitHub, and will set up leaderboards for developers to benchmark and compare progress.
Facebook also said its data centers will reach net zero emissions by the end of 2020.