AI paves the way for cheaper green hydrogen production

Researchers at the University of Toronto are using artificial intelligence (AI) to speed up the discovery of sustainable energy solutions. Using the Canadian Light Source at the University of Saskatchewan, the team validated an AI-designed catalyst that they claim efficiently produces hydrogen fuel.

Green hydrogen is produced by running electricity from renewable sources between two metal electrodes in water, releasing hydrogen and oxygen gases. 

However, this process currently requires a lot of electricity and uses rare, costly metals. 

“In a nutshell, the problem is we want renewable hydrogen and to do that we often split water into hydrogen and oxygen and the current state of the art membranes based on nafion are are acidic and a lot of metals dissolve under the acidic conditions,” explained John Kitchin, one of the team of researchers involved in the project.

This encouraged scientists to look for an alloy that could serve as a more efficient and affordable catalyst. 

Finding the right combination of metals typically involves a lengthy trial-and-error process, but AI can significantly streamline this search.

Speaking with Canadian Light Source, researcher Dr. Jehad Abed, said, “We’re talking about hundreds of millions or billions of alloy candidates, and one of them could be the right answers.”

The team employed AI to predict the most effective combination of metals that would make up a catalyst.

According to CLS, the team took over 36,000 different metal oxide combinations and ran virtual simulations to assess which combination of ingredients might work the best.

The winning candidate was a combination of ruthenium, chromium and titanium in specific proportions.

“After identifying the candidate, we can now go to the lab, make the candidate material, and then test it in a real device,” said Abed.

At the CLS, the researchers have access to beamlines, stations that can shine a very bright beam of light into the catalyst material during the reaction itself.

“This allowed us to not only create the most efficient catalyst, but also understand important things about the underlying mechanism at play.”

Abed revealed that the computer’s recommended alloy performed 20 times better than the team’s benchmark metal in terms of stability and durability.

“The computer was right about this alloy being more effective and stable. That was a breakthrough because it shows that this method for finding better catalysts is working,” said Abed, speaking with CLS. “What would take a person years to test, the computer can simulate in a matter of days.”

Using AI to reduce emissions

AI is enhancing sustainability in industrial gases and energy through various innovations. In chemical production, AI optimises processes to reduce energy use and waste, like BASF’s ammonia production improvements. 

For carbon capture, AI at NET Power maximises CO2 capture efficiency. Safety and efficiency are enhanced with AI-driven predictive maintenance, used by ExxonMobil. 

A study from the University of Surrey found that, using AI, carbon capture facilities could capture 16.7% more CO2 while using 36.3% less energy from the National Grid at coal-fired power stations.

Companies like Siemens Gamesa use AI to integrate renewable energy in hydrogen production effectively while industrial gas giant Linde uses AI to reduce energy use in air separation units. 

AI also supports circular economy practices, like Covestro’s CO2 recycling. It optimises supply chains for companies like Air Products, reducing emissions. 

Honeywell uses AI to design energy-efficient equipment, and Dow Chemical applies AI for real-time energy management, cutting waste.