Presenting SLAMD - A Sequential Learning Based Software for the Inverse Design of Sustainable Cementitious Materials

The number of components in concrete has increased in recent decades - especially in formulations with a reduced carbon footprint. Through the type of binder, supplementary cementitious materials, activators, concrete admixtures, recycled aggregates, etc., attempts are made not only to improve the material properties but also to reduce the ecological and economic impact of concrete as the most widely used material of humankind. Cementitious materials are nanoscale materials. This is accompanied by a more inconsistent composition of raw materials, which makes an experimental tuning of formulations more and more necessary. However, the increased complexity in composition presents a challenge in finding the ideal formulation through trial and error. Inverse design (ID) techniques offer a solution to this challenge by allowing for a comprehensive search of the entire design space to create new and improved concrete formulations. In this publication, we introduce the concept of ID and demonstrate how our opensource app “SLAMD” provides all necessary steps of the workflow to adapt it in the laboratory, lowering the application barriers. The intelligent screening process, guided by a predictive model, leads to a more efficient and effective data-driven material design process resulting in reduced carbon footprint and improved material quality while considering socio-economic factors in the materials design.