SYDNEY, June 19 (Xinhua) -- Australian scientists have used artificial intelligence (AI) to find the best catalyst for green ammonia production, making the process far more efficient and eco-friendlier.

Rather than testing over 8,000 possible metal catalyst combinations in the lab, researchers used AI to predict the most promising options, narrowing their experiments to just 28, said a news release issued by the University of New South Wales (UNSW) Sydney on Thursday.

AI also helps researchers discover a highly effective catalyst made from iron, bismuth, nickel, tin, and zinc, which is described as "exceeding their most optimistic expectation," the release said.

The new process boosts ammonia production sevenfold and achieves near-total energy efficiency at just 25 degrees Celsius, far surpassing conventional methods, said the study published in the journal Small.

Traditionally, ammonia, a vital component in fertilizers, has been produced using the energy-intensive Haber-Bosch process, which consumes vast amounts of energy and is responsible for about 2 percent of global greenhouse gas emissions, it said.

The new improvement in green ammonia production is being tested in compact, farm-ready units that let farmers produce fertilizer on-site with renewable energy, cutting transport emissions, said Ali Jalili from UNSW's School of Chemistry.

"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," Jalili said.

This AI-driven method speeds up discovery and enables scalable, affordable green ammonia, marking a major step toward decarbonizing agriculture worldwide, he said. ■