Predicting the rheology of limestone calcined clay cements (LC³): Linking composition and hydration kinetics to yield stress through Machine Learning

The physicochemical characteristics of calcined clay influence yield stress of limestone calcined clay cements (LC³), but the independent influences the clay's physical and chemical characteristics as well as the effect of other variables on LC³ rheology are less well-understood. Further, a relationship between LC³ hydration kinetics and yield stress – important for informing mixture design – has not yet been established. Here, rheological properties were determined in pastes with varying water-to-solid ratio (w/s), constituent mass ratios (PC:metakaolin:limestone), limestone particle size and gypsum content. From these data, an ML model developed allowed the independent examination of the different mechanisms by which metakaolin fraction influences yield stress of LC³, identifying four predictors – packing index, Al₂O₃/SO₃, total particle density and metakaolin fraction relative to limestone (MK/LS) – most significant for predicting LC³ yield stress. A methodology based on kernel smoothing also identified hydration kinetics parameters best correlated with yield stress.