The sun doesn’t always shine and to store energy[batteries] in its absence may be a costly affair. So, with all this mention going green, how is it possible to incentivise people towards futuristic yet unsustainable and expensive goals?

To address this challenge, Facebook AI and therefore the Carnegie Mellon University (CMU) have announced the Open Catalyst Project, a collaboration intended to use AI to accelerate quantum mechanical simulations by 1,000x so as to get new electrocatalysts needed for more efficient and scalable ways to store and use renewable energy.

The goal of the Open Catalyst Project, stated the Facebook AI team, is to get low-cost catalysts so as to seek out solutions that are good alternatives of current solutions that are inefficient or believe rare and expensive electrocatalysts like platinum, limiting their practicality.

The researchers have identified a use case for machine learning but now comes the important challenge—data. So, the team at FAIR and CMU have even addressed this problem by releasing a dataset called the OC20. The OC20 data set comprises over 1.3 million relaxations of molecular adsorptions onto surfaces, the most important data set of electrocatalyst structures so far .

Finding efficient storage techniques is additionally a cloth science problem. The properties change with change in chemistry; the way interactions happen at the atomic level is crucial. At the atomic scale, the amount of combinations of interactions is difficult to predict. Scientists believe quantum mechanical simulation tools like density functional theory(DFT).

“Producing this data set also required a considerable amount of engineering expertise and computing power. We ran DFT simulations on spare compute cycles over a period of 4 months. Facebook’s data centres will reach net zero emissions by the top of the year, making this a responsible and sustainable thanks to run the compute-intensive calculations necessary to create this data set,” said Facebook.

Key Takeaways

  1. Calculations that take modern laboratories days, with the assistance of AI, could only take a couple of seconds.
  2. Success could inaugurate the widespread adoption of renewable energy, as costs come down and impact on the grid is mitigated by better storage.
  3. The implications for water quality remediation, medical treatment development, advanced manufacturing, or geochemistry.
  4. Current baseline models are still faraway from being useful in practical applications, so there’s still much to be accomplished to understand the renewable energy solutions are needed.

By Joseph

Leave a Reply

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