CGCNN-HD model architecture. Image credit: Journal of the American Chemical Society (2024). DOI: 10.1021/jacs.4c01353
Researchers at the University of Toronto are using artificial intelligence to accelerate scientific breakthroughs in the search for sustainable energy. They have used the Canadian Light Source (CLS) at the University of Saskatchewan (USask) to confirm that an AI-generated “recipe” for a new catalyst offers a more efficient method of producing hydrogen fuel.
To produce green hydrogen, electricity generated from renewable resources is passed between two pieces of metal in water, releasing oxygen and hydrogen gases. The problem with this process is that it currently requires a lot of electricity and the metals used are rare and expensive.
Researchers are looking for the right alloy or combination of metals that could act as a catalyst to make this reaction more efficient and less expensive. Traditionally, this search would involve trial and error in the lab, but when trying to find the proverbial needle in a haystack, this approach is too time-consuming.
“We are talking about hundreds of millions or billions of alloy candidates, and one of them could be the right answer,” says Jehad Abed. He was part of a team that developed a computer program to significantly speed up this search.
The results are published in Journal of the American Chemical SocietyAt the time of this project, Abed was a doctoral student under the supervision of Edward Sargent at the University of Toronto and working with scientists at Carnegie Mellon University.
The AI program the team developed looked at over 36,000 different metal oxide combinations and ran virtual simulations to determine which combination of ingredients might work best. Abed then tested the program’s best candidate in the lab to see if its predictions held true.
The team used the CLS’s ultra-bright X-rays to analyze the catalyst’s performance during a reaction. “We had to use this very bright light from the Canadian Light Source to shine it on our material and see how the atomic arrangements change and respond to the amount of electricity we feed into it,” Abed said. The researchers also used the Advanced Photon Source at Argonne National Laboratory in Chicago.
The alloy, a combination of the metals ruthenium, chromium and titanium in certain proportions, was the clear winner, according to Abed.
“The alloy recommended by the computer was 20 times better than our reference metal in terms of strength and durability,” he said. “It lasted a long time and worked efficiently.”
While the AI program developed by Jehad and his colleagues is very promising, the material itself still needs to undergo numerous tests to ensure that it holds up under “real-world” conditions.
“The computer was right that this alloy is more effective and stable. This was a breakthrough because it shows that this method of developing better catalysts works,” said Abed. “What a human would test for years, the computer can simulate in a few days.”
The researchers are confident that AI will help us more quickly find the answers we need to make green energy widely available.
Further information:
Jehad Abed et al, Pourbaix Machine Learning Framework identifies acidic water oxidation catalysts exhibiting suppressed ruthenium dissolution, Journal of the American Chemical Society (2024). DOI: 10.1021/jacs.4c01353
Provided by Canadian Light Source
Quote: Team uses AI to find cheaper way to produce green hydrogen (August 29, 2024), accessed August 29, 2024 from https://phys.org/news/2024-08-team-ai-cheaper-green-hydrogen.html
This document is subject to copyright. Except for the purposes of private study or research, no part of it may be reproduced without written permission. The contents are for information purposes only.
