Prediction of Elastic Modulus for Fibre-Reinforced Soil-Cement Mixtures: A Machine Learning Approach

Soil-cement mixtures reinforced with fibres are an alternative method of chemical soil stabilisation in which the inherent disadvantage low or no tensile flexural strength is overcome by incorporating fibres. These require a significant amount time and resources for comprehensive laboratory characterisation, because considerable number parameters involved. Therefore, implementation Machine Learning (ML) approach provides way to predict mechanical properties soil-cement In this study, Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Random Forest (RF), Multiple Regression (MR) algorithms were trained predicting elastic modulus For ML training, dataset 121 records was used, comprising 16 composite material (soil, binder, fibres). ANN RF showed promising determination coefficient (R2 ≥ 0.93) on prediction. Moreover, results proposed models consistent findings that fibre binder content have effect modulus.