{"id":164916,"date":"2025-07-01T07:39:00","date_gmt":"2025-07-01T05:39:00","guid":{"rendered":"https:\/\/renewable-carbon.eu\/news\/?p=164916"},"modified":"2025-06-27T13:38:08","modified_gmt":"2025-06-27T11:38:08","slug":"ai-paves-the-way-towards-green-cement","status":"publish","type":"post","link":"https:\/\/renewable-carbon.eu\/news\/ai-paves-the-way-towards-green-cement\/","title":{"rendered":"AI paves the way towards green cement"},"content":{"rendered":"\n\n
\n
\"When<\/a>
When cement is mixed with water, sand and gravel, it becomes concrete \u2013 the most widely used building material in the world. However, the production of cement releases large amounts of carbon dioxide. Researchers at PSI are using artificial intelligence and computational modelling to develop alternative formulations that should be more climate-friendly.
\u00a9 Paul Scherrer Institute PSI\/Markus Fischer<\/figcaption><\/figure><\/div>\n\n\n

The cement industry produces around eight percent of global CO\u2082 emissions \u2013 more than the entire aviation sector worldwide. Researchers at the Paul Scherrer Institute PSI have developed an AI-based model that helps to accelerate the discovery of new cement formulations that could yield the same material quality with a better carbon footprint.<\/strong><\/p>\n\n\n\n

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. Unsurprisingly, such temperatures typically can’t be achieved with electricity alone. They are the result of energy-intensive combustion processes that emit large amounts of carbon dioxide (CO\u2082). What may be surprising, however, is that the combustion process accounts for less than half of these emissions, far less. The majority is contained in the raw materials needed to produce clinker and cement: CO\u2082 that is chemically bound in the limestone is released during its transformation in the high-temperature kilns.<\/p>\n\n\n\n

One promising strategy for reducing emissions is to modify the cement recipe itself \u2013 replacing some of the clinker with alternative cementitious materials. That is exactly what an interdisciplinary team in the Laboratory for Waste Management in PSI\u2019s Center for Nuclear Engineering and Sciences has been investigating. Instead of relying solely on time-consuming experiments or complex simulations, the researchers developed a modelling approach based on machine learning.  <\/p>\n\n\n\n

\n

\u201cThis allows us to simulate and optimise cement formulations so that they emit significantly less CO\u2082 while maintaining the same high level of mechanical performance,\u201d explains mathematician Romana Boiger, first author of the study.<\/strong> \u201cInstead of testing thousands of variations in the lab, we can use our model to generate practical recipe suggestions within seconds \u2013 it’s like having a digital cookbook for climate-friendly cement.\u201d<\/p>\n<\/blockquote>\n\n\n\n

With their novel approach, the researchers were able to selectively filter out those cement formulations that could meet the desired criteria. <\/p>\n\n\n\n

\n

\u201cThe range of possibilities for the material composition \u2013 which ultimately determines the final properties \u2013 is extraordinarily vast,\u201d says Nikolaos Prasianakis, head of the Transport Mechanisms Research Group at PSI, who was the initiator and co-author of the study<\/strong>. \u201cOur method allows us to significantly accelerate the development cycle by selecting promising candidates for further experimental investigation.\u201d <\/p>\n<\/blockquote>\n\n\n\n

The results of the study were published in the journal Materials and Structures<\/em>.<\/p>\n\n\n\n

The right recipe<\/strong><\/h3>\n\n\n\n

Already today, 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 and thus reduce CO\u2082 emissions. However, the global demand for cement is so enormous that these materials alone cannot meet the need. <\/p>\n\n\n\n

\n

\u201cWhat we need is the right combination of materials that are available in large quantities and from which high-quality, reliable cement can be produced,\u201d says John Provis, head of the Cement Systems Research Group at PSI and co-author of the study.<\/strong><\/p>\n<\/blockquote>\n\n\n

\n
\"\"<\/figure><\/div>\n\n\n

<\/a>Cement is what holds our modern world together. This inconspicuous powder, when mixed with sand, gravel and water, becomes concrete \u2013 a building material that can be transported almost anywhere and cast into almost any shape imaginable. Concrete is multifunctional and durable, making it an indispensable part of our infrastructure.<\/p>\n\n\n\n

The sheer amount of cement this requires is almost impossible to comprehend. <\/p>\n\n\n\n

\n

\u201cTo put it bluntly, humanity today consumes more cement than food \u2013 around one and a half kilograms per person per day,\u201d says John Provis, head of the Cement Systems Research Group at PSI and co-author of the study<\/strong>. \u201cThese are unimaginable quantities. If we could improve the emissions profile by just a few percent, this would correspond to a carbon dioxide reduction equivalent to thousands or even tens of thousands of cars,\u201d the cement chemist says.<\/p>\n\n\n\n

Finding such combinations, however, is challenging: \u201cCement is basically a mineral binding agent \u2013 in concrete, we use cement, water, and gravel to artificially create minerals that hold the entire material together,\u00bb Provis <\/strong>explains. \u201cYou could say we’re doing geology in fast motion.\u201d <\/p>\n<\/blockquote>\n\n\n\n

This geology \u2013 or rather, the set of physical processes behind it \u2013 is enormously complex, and modelling it on a computer is correspondingly computationally intensive and expensive. That is why the research team is relying on artificial intelligence.<\/p>\n\n\n

\n
\"Pictured<\/a>
A cement chemist, a mathematician and an engineer \u2013 and more: The team at PSI brings together expertise from a range of disciplines. It is only thanks to this interdisciplinary approach that the researchers were able to develop their AI-supported optimisation approach. Pictured (from left to right): John Provis, Romana Boiger, and Nikolaos Prasianakis. \u00a9 Paul Scherrer Institute PSI\/Markus Fischer<\/figcaption><\/figure><\/div>\n\n\n

AI as computational accelerator<\/strong><\/h3>\n\n\n\n

Artificial neural networks are computer models that are trained, using existing data, to speed up complex calculations. During training, the network is fed a known data set and learns from it by adjusting the relative strength or \u201cweighting\u201d of its internal connections so that it can quickly and reliably predict similar relationships. This weighting serves as a kind of shortcut \u2013 a faster alternative to otherwise computationally intensive physical modelling.<\/p>\n\n\n\n

The researchers at PSI also made use of such a neural network. <\/p>\n\n\n\n

\n

They themselves generated the data required for training: \u201cWith the help of the open-source thermodynamic modelling software GEMS, developed at PSI, we calculated \u2013 for various cement formulations \u2013 which minerals form during hardening and which geochemical processes take place,\u201d explains Nikolaos Prasianakis. <\/strong><\/p>\n<\/blockquote>\n\n\n\n

By combining these results with experimental data and mechanical models, the researchers were able to derive a reliable indicator for mechanical properties \u2013 and thus for the material quality of the cement. For each component used, they also applied a corresponding CO\u2082 factor, a specific emission value that made it possible to determine the total CO\u2082 emissions. <\/p>\n\n\n\n

\n

\u201cThat was a very complex and computationally intensive modelling exercise,\u201d the scientist says.<\/p>\n<\/blockquote>\n\n\n\n

But it was worth the effort \u2013 with the data generated in this way, the AI model was able to learn. <\/p>\n\n\n\n

\n

\u201cInstead of seconds or minutes, the trained neural network can now calculate mechanical properties for an arbitrary cement recipe in milliseconds \u2013 that is, around a thousand times faster than with traditional modelling,\u201d Boiger<\/strong> explains. <\/p>\n<\/blockquote>\n\n\n\n

From output to input<\/strong><\/h3>\n\n\n\n

How can this AI now be used to find optimal cement formulations \u2013 with the lowest possible CO\u2082 emissions and high material quality? One possibility would be to try out various formulations, use the AI model to calculate their properties, and then select the best variants. A more efficient approach, however, is to reverse the process. Instead of trying out all options, ask the question the other way around: Which cement composition meets the desired specifications regarding CO\u2082 balance and material quality?<\/p>\n\n\n\n

Both the mechanical properties and the CO\u2082 emissions depend directly on the recipe. <\/p>\n\n\n\n

\n

\u201cViewed mathematically, both variables are functions of the composition \u2013 if this changes, the respective properties also change,\u201d the mathematician<\/strong> explains. <\/p>\n<\/blockquote>\n\n\n\n

To determine an optimal recipe, the researchers formulate the problem as a mathematical optimisation task: They are looking for a composition that simultaneously maximises mechanical properties and minimises CO\u2082 emissions.  <\/p>\n\n\n\n

\n

\u201cBasically, we are looking for a maximum and a minimum \u2013 from this we can directly deduce the desired formulation,\u201d the mathematician<\/strong> says.<\/p>\n<\/blockquote>\n\n\n\n

To find the solution, the team integrated in the workflow an additional AI technology, the so-called genetic algorithms \u2013 computer-assisted methods inspired by natural selection. This enabled them to selectively identify formulations that ideally combine the two target variables. <\/p>\n\n\n\n

The advantage of this \u201creverse approach\u201d: You no longer have to blindly test countless recipes and then evaluate their resulting properties; instead you can specifically search for those that meet specific desired criteria \u2013 in this case, maximum mechanical properties with minimum CO\u2082 emissions.<\/p>\n\n\n\n

Interdisciplinary approach with great potential<\/strong><\/h3>\n\n\n\n

Among the cement formulations identified by the researchers, there are already some promising candidates.<\/p>\n\n\n\n

\n

\u201cSome of these formulations have real potential,\u201d says John Provis<\/strong>, \u201cnot only in terms of CO\u2082 reduction and quality, but also in terms of practical feasibility in production.\u201d To complete the development cycle, however, the recipes must first be tested in the laboratory.  \u201cWe’re not going to build a tower with them right away without testing them first,\u201d Nikolaos Prasianakis<\/strong> says with a smile. <\/p>\n<\/blockquote>\n\n\n\n

The study primarily serves as a proof of concept \u2013 that is, as evidence that promising formulations can be identified purely by mathematical calculation. <\/p>\n\n\n\n

\n

\u201cWe can extend our AI modelling tool as required and integrate additional aspects, such as the production or availability of raw materials, or where the building material is to be used \u2013 for example, in a marine environment, where cement and concrete behave differently, or even in the desert,\u201d says Romana Boiger. Nikolaos Prasianakis<\/strong> is already looking ahead: \u201cThis is just the beginning. The time savings offered by such a general workflow are enormous \u2013 making it a very promising approach for all sorts of material and system designs.\u201d<\/p>\n\n\n\n

Without the interdisciplinary background of the researchers, the project would never have come to fruition: \u201cWe needed cement chemists, thermodynamics experts, AI specialists \u2013 and a team that could bring all of this together,\u201d Prasianakis<\/strong> says. \u201cAdded to this was the important exchange with other research institutions such as EMPA within the framework of the SCENE project.\u201d <\/p>\n<\/blockquote>\n\n\n\n

SCENE (the Swiss Centre of Excellence on Net Zero Emissions) is an interdisciplinary research programme that aims to develop scientifically sound solutions for drastically reducing greenhouse gas emissions in industry and the energy supply. The study was carried out as part of this project.<\/p>\n","protected":false},"excerpt":{"rendered":"

The cement industry produces around eight percent of global CO\u2082 emissions \u2013 more than the entire aviation sector worldwide. Researchers at the Paul Scherrer Institute PSI have developed an AI-based model that helps to accelerate the discovery of new cement formulations that could yield the same material quality with a better carbon footprint. The rotary […]<\/p>\n","protected":false},"author":59,"featured_media":164936,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_seopress_robots_primary_cat":"none","nova_meta_subtitle":"Researchers at the Paul Scherrer Institute PSI have developed an AI-based model that helps to accelerate the discovery of new cement formulations","footnotes":""},"categories":[5572],"tags":[24550,5838,12447,15692,11749],"supplier":[959],"class_list":["post-164916","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-bio-based","tag-arteficialintelligence","tag-bioeconomy","tag-buildingmaterials","tag-cement","tag-construction","supplier-paul-scherrer-institut-psi"],"_links":{"self":[{"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/posts\/164916","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/users\/59"}],"replies":[{"embeddable":true,"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/comments?post=164916"}],"version-history":[{"count":0,"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/posts\/164916\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/media\/164936"}],"wp:attachment":[{"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/media?parent=164916"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/categories?post=164916"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/tags?post=164916"},{"taxonomy":"supplier","embeddable":true,"href":"https:\/\/renewable-carbon.eu\/news\/wp-json\/wp\/v2\/supplier?post=164916"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}