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 limestone cements (LC3), but the independent influences clay's physical and chemical as well effect other variables on LC3 rheology are less well-understood. Further, a relationship between hydration kinetics – 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), particle size gypsum content. From these data, an ML model developed allowed examination different mechanisms by which metakaolin fraction LC3, identifying four predictors packing index, Al2O3/SO3, total density relative to (MK/LS) most significant predicting stress. A methodology based kernel smoothing also identified parameters best correlated