�����Ʊ

To find the best catalyst for green ammonia, researchers were staring down 8000 lab experiments. With AI, they only needed 28.

Scientists and engineers at �����Ʊ Sydney, who previously developed a method for making green ammonia, have now turned to artificial intelligence and machine learning to make the process even more efficient.

Ammonia, a nitrogen-rich substance found in fertiliser, is often credited with saving much of the world from famine in the 20th century. But its benefit to humankind has come at a cost, with one of the largest carbon footprints of all industrial processes. To produce it, industrial plants need temperatures of more than 400°C and extremely high pressures – more than 200 times normal atmospheric pressure. Such energy-intensive requirements have made ammonia production a major contributor to global greenhouse gas emissions, accounting for 2% worldwide.

But in 2021, a �����Ʊ team discovered a way to make ammonia from air and water using renewable energy, at about the same temperature as a warm summer’s day.

Dr Ali Jalili, with �����Ʊ’s School of Chemistry, says while the original proof-of-concept demonstrated that ammonia could be created entirely from renewable energy, at low temperatures and without emitting carbon, there was still room for improvement. For example, could it be produced more efficiently, using lower energy, less wasted energy and producing more ammonia?

To answer these questions, the team needed to find the right catalyst – a substance that speeds up the chemical reaction without being consumed by it. As they explained in the paper published today in the journal , the team began by coming up with a shortlist of promising catalyst candidates.

“We selected 13 metals that past research said had the qualities we wanted – for example, this metal is good at absorbing nitrogen, this one is good at absorbing hydrogen and so on,” Dr Jalili says.

“But the best catalyst would need a combination of these metals, and if you do the maths, that turns out to be more than 8000 different combinations.”

Enter artificial intelligence

The researchers fed a machine learning system information about how each metal behaves and trained it to spot the best combinations. That way, instead of having to run more than 8000 experiments in the lab, they only had to run 28.

“AI drastically reduced discovery time and resources, replacing thousands of trial-and-error experiments,” says Dr Jalili.

“Having a shortlist of 28 different combinations of metals meant we saved a huge amount of time in lab work compared to if we’d had to test all 8000 of them, which was simply not possible.”

The winning combo was a mix of iron, bismuth, nickel, tin and zinc. While the researchers were expecting some improvement in the process of producing green ammonia, this new five-metal catalyst exceeded even their most optimistic expectations.

“We achieved a sevenfold improvement in the ammonia production rate and at the same time it was close to 100% efficient, meaning almost all of the electrical energy we needed to make the reaction happen was used to make ammonia — very little was wasted.”

Known as Faradaic efficiency, high efficiency scores mean the process is more sustainable, cost-effective, and scalable, which is crucial for making green ammonia a viable alternative to fossil-fuel-based methods. Dr Jalili says his team was able to make ammonia this way at an ambient 25°C, less than 10% of the temperature required to make ammonia the conventional way via the .

“This low-temperature, high-efficiency approach makes green ammonia production viable and scalable. We believe it can compete directly with electrified Haber–Bosch and even fossil-based routes, creating a realistic pathway for truly green ammonia.”

Farming out production

Looking ahead, Dr Jalili and his research team hope the new improvement in green ammonia production can lead to real-world impact. The goal is that one day soon, farmers will be able to produce ammonia for fertilisers onsite, at low cost and low energy, eliminating the need for delivery via transport routes, further reducing the carbon footprint of ammonia production.

In fact, localised ammonia production has already begun, although it’s still in trial phase. Farmers can buy or lease ammonia modules which are compact, factory-built systems the size of a shipping container. Each module combines the AI-optimised catalyst, plasma generator and electrolyser into a single plug-and-play package.

“For a century, ammonia production was based on massive, centralised factories that cut costs by operating at enormous scales, but those projects take years to build, require billions of dollars in capital, and cannot adapt quickly as energy markets change,” Dr Jalili says.

“Our approach breaks away from the era of centralised, giga-scale plants and opens the door for smaller, decentralised units that require much lower upfront investments.”

Hydrogen energy storage

Another benefit of low-cost, low energy ammonia production is the role it can play in the world’s move towards a hydrogen economy. Liquid ammonia stores more hydrogen energy than liquid hydrogen, which means it’s a better contender for renewable energy storage and transportation.

“This same system doubles as a carbon-free hydrogen carrier, creating new economic opportunities that align with the global shift to a clean hydrogen economy,” Dr Jalili says.

Building on their farm-scale proof of nitrogen fertiliser production, Dr Jalili’s team is now deploying their AI-discovered catalyst in distributed ammonia modules to cut costs, sharpen green ammonia’s competitiveness, and accelerate its uptake in the global market.