AI-Guided Electrocatalytic Ammonia Synthesis: Catalytic Interface Design for Carbon-Neutral Energy and Climate Change Mitigation

The conventional Haber–Bosch process for synthesizing ammonia (NH₃) relies primarily on fossil fuels and is highly energy-intensive, accounting for about 2% of annual CO₂ emissions. In addition, widespread use of NH3-based fertilizers contributes indirectly to N₂O emissions, a potent greenhouse gas, highlighting the urgent need for low-carbon alternatives. Renewable-powered electrochemical nitrogen reduction reaction (NRR) emerges as a pivotal technology for greenhouse gas mitigation, facilitating the sustainable production of “green NH3,” curtailing CO2 emissions, and enabling carbon-neutral energy storage. In this project, we propose to demonstrate an innovative, low-carbon pathway for NH₃ production through solar-powered electrocatalytic nitrogen reduction. Central to this effort is the artificial intelligence (AI) and machine learning (ML)-assisted design and integration of catalytic interfaces that enable efficient coupling of N₂ activation with water oxidation under mild conditions. The project will create a sustainable and economically viable route to green ammonia while reducing CO₂ emissions.

“In this Seed Fund project, we leverage AI/ML to help design catalytic interfaces that enable efficient nitrogen reduction reactions under mild conditions, promising for a sustainable and economically viable route to green ammonia while reducing CO₂ emissions.”

Junhong Chen, Crown Family Professor of Molecular Engineering, Pritzker School of Molecular Engineering