Swiss researchers have created an AI system that writes climate-friendly cement recipes in seconds, potentially transforming one of the world's most carbon-intensive industries.
The team at the Paul Scherrer Institute (PSI) developed a machine learning approach that can dramatically cut cement's carbon footprint by redesigning its recipe. Their system simulates thousands of ingredient combinations, pinpointing those that maintain structural integrity while emitting far less CO2—all in seconds.
The innovation targets a significant climate challenge, as the cement industry produces around eight percent of global CO2 emissions—more than the entire aviation sector worldwide. The rotary kilns in cement plants are heated to a scorching 1,400 degrees Celsius to burn ground limestone down to clinker, the raw material for ready-to-use cement.
Surprisingly, less than half of cement's emissions come from the combustion process itself. The majority is released from the raw materials: CO₂ chemically bound in limestone is released during its transformation in high-temperature kilns.
One promising strategy for reducing emissions is modifying the cement recipe by replacing some of the clinker with alternative cementitious materials. That's exactly what the interdisciplinary team at PSI's Laboratory for Waste Management has been investigating.
"This allows us to simulate and optimise cement formulations so that they emit significantly less CO2 while maintaining the same high level of mechanical performance," explains mathematician Romana Boiger, first author of the study. "Instead of testing thousands of variations in the lab, we can use our model to generate practical recipe suggestions within seconds—it's like having a digital cookbook for climate-friendly cement."
Industrial by-products such as slag from iron production and fly ash from coal-fired power plants are already being used to partially replace clinker in cement formulations. However, global cement demand is so enormous that these materials alone cannot meet the need. "What we need is the right combination of materials that are available in large quantities and from which high-quality, reliable cement can be produced," says John Provis, head of the Cement Systems Research Group at PSI and co-author of the study.
The project required an interdisciplinary approach, bringing together cement chemists, thermodynamics experts, and AI specialists. It was conducted as part of SCENE (the Swiss Centre of Excellence on Net Zero Emissions), an interdisciplinary research programme that aims to develop scientifically sound solutions for drastically reducing greenhouse gas emissions in industry and energy supply.
The research was published in the journal Materials and Structures, offering a promising path toward decarbonizing one of the most challenging sectors in the fight against climate change.