Sustainable Construction Analytics: Smart Modeling for Compressive Strength Prediction in Arabic Gum-Modified Mortar

Abstract

Utilizing waste materials in mortar and concrete as renewable resources to safeguard the environment is emerging as a significant area for land cleanup. Among the diverse sources of waste materials, agriculture stands out, presenting various types of byproducts. Arabic gum, extracted from trees across different countries, is recognized for its multiple benefits, particularly in pharmaceutical and food industries. Numerous studies have explored the potential of Arabic gum as a partial substitute for cement in mortar. This article focuses on gathering experimental data from existing literature on the use of Arabic gum in mortar as a partial replacement for cement. It aims to develop a statistical model to predict the compressive strength of mortar. Various forms of statistical and machine learning models, such as linear regression (LR), non-linear regression (NLR), stepwise regression (SWR), the Gaussian process regression (GPR), and artificial neural network (ANN), were employed, and the most robust model was selected. The models were assessed using different statistical parameters, including the coefficient of determination, mean absolute error, root mean square error, and scatter index. The results revealed that the artificial neural network (ANN) exhibited the highest efficiency compared to other models.