Machine learning approaches to predict compressive strength of fly ash-based geopolymer concrete: A comprehensive review

Abstract

Geopolymer concrete is a sustainable replacement to the Ordinary Portland Cement (OPC) concrete as it mitigates some of the associated problems of OPC manufacturing such as greenhouse gas emission and natural resource depletion. There has been significant recent research in the design of fly ash-based geopolymer concrete using advanced machine learning techniques which can address some of the problems with classical mix design approaches. However, practical application of geopolymer concrete is limited due to lack of standard mix design procedure. This comprehensive review summarizes the current literature on machine learning methodologies to predict the compressive strength of fly ash-based geopolymer concrete. Firstly, the input parameters used for the machine learning model development are categorized based on feature selection or feature extraction. Secondly, available machine learning approaches are categorized based on analysis methods namely, nonlinear regression, ensemble learning, and evolutionary programming. The effect of hyperparameters on the individual model performance, and model comparison based on the prediction performance are also discussed to identify potentially more suitable model type and hyper parameter ranges. Further, the paper discusses the input variable’s sensitivity towards the model performance which provides guidance towards future model developments. Overall, this paper will provide an understanding of the current state of machine learning approaches to predict the compressive strength of geopolymer concrete and the gaps in research for the development of models and achieving the required performance. Hence, the summarized knowledge will be highly beneficial to design prospective research towards sustainable cement-free concrete using fly ash.