An experimental investigation was conducted to synthesise an alkali-activated binder using natural pozzolan and limestone powder. The effect of the mix parameters such as the binder ratio, NaOH molarity (4 -14 M), curing temperature (25 -90 °C), sodium silicate to sodium hydroxide ratio (0.5 -1.5), fine aggregate to binder ratio (1.4 -2.2), alkaline activator to binder ratio (0.45 -0.55) and curing days (1,3,7,14,28) were determined on the compressive strength of the mortar. A stepwise regression algorithm was developed to estimate the compressive strength of the mortar. Five different models (I-V) were developed using 130 experimental data sets with seven descriptors. Bayesian information criterion (BIC), Akaike's information criterion (AIC) and the sum of square error (SSE) criteria were used to fit the developed model in order to select the best model. The cubic with interactions model (V) is characterised with a high correlation coefficient (97.2 %), the lowest root means square error (1.672), and the lowest mean absolute error (1.313) in comparison with the other four models (I-IV). The outcomes of this work could provide an effective and efficient way of modelling the compressive strength of environmentally friendly binders with minimal experimental stress, limit the uncertainties and errors inherent in a laboratory.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.