Cement is essential to our modern infrastructure—but its production is a climate nightmare. Now, Swiss researchers have harnessed AI to change that.
Key Points at a Glance
- The cement industry is responsible for ~8% of global CO₂ emissions.
- Most emissions come from limestone calcination, not just fuel combustion.
- AI models now optimize greener cement recipes with less CO₂ and equal strength.
- Machine learning speeds up discovery from hours to milliseconds.
- New “digital cookbook” approach may reshape the future of construction materials.
Producing cement emits more CO₂ than global air travel. The culprit isn’t just fossil fuel combustion; it’s chemistry. Limestone, the core ingredient of cement, releases bound carbon dioxide when heated to 1,400°C in rotary kilns. Reducing that embedded CO₂ has been a major hurdle—until now.
At the Paul Scherrer Institute (PSI), researchers have developed a machine learning approach that acts like a digital alchemist, generating thousands of eco-friendly cement formulations at record speed. This new study, published in Materials and Structures, suggests that cement, long a climate problem, could now be part of the solution.
“Instead of testing thousands of variations in the lab, we use our model to generate practical recipe suggestions within seconds,” said Dr. Romana Boiger, lead author and mathematician. “It’s like having a digital cookbook for climate-friendly cement.”
By integrating thermodynamic modeling, experimental data, and mechanical predictions, PSI’s model rapidly identifies promising recipes. These formulations substitute some clinker—cement’s CO₂-heavy ingredient—with alternative, less carbon-intensive materials. The neural network learns the relationship between ingredients and performance, generating reliable suggestions 1,000 times faster than traditional methods.
Even more impressive: PSI scientists flipped the process. Instead of calculating the performance of each cement blend, they asked AI to find formulations that already match desired outcomes—low emissions and high strength. This reverse engineering approach uses genetic algorithms, inspired by evolution, to solve for the optimal mix.
“We’re doing geology in fast motion,” said Dr. John Provis, cement chemist and co-author. “You could say we’re creating artificial minerals tailored for construction—but with a fraction of the carbon cost.”
Humanity uses 1.5 kg of cement per person per day. Even a small improvement in its emissions profile could mean massive CO₂ reductions. The AI-assisted formulations, once validated in labs, could reshape global construction practices—especially in regions with limited access to industrial byproducts like fly ash or slag.
This breakthrough is part of the SCENE initiative (Swiss Centre of Excellence on Net Zero Emissions), merging thermodynamics, materials science, and AI. According to Dr. Nikolaos Prasianakis, “This is just the beginning. The time savings offered by this approach are enormous—it’s a promising model for designing all sorts of sustainable materials.”
Source: Paul Scherrer Institute
Enjoying our articles?
We don’t show ads — so you can focus entirely on the story, without pop-ups or distractions. We don’t do sponsored content either, because we want to stay objective and only write about what truly fascinates us. If you’d like to help us keep going — buy us a coffee. It’s a small gesture that means a lot. Click here – Thank You!
