Hybrid machine learning for predicting strength of sustainable concrete

Foamed concrete material is a sustainable material which is widely used in the construction industry due to their sustainability. Accurate prediction of their compressive strength is vital for structural design. However, empirical methods are limited to consider simultaneously all influencing factors in predicting the compressive strength of foamed concrete materials. Thus, this study proposed a novel hybrid artificial intelligence (AI) model which couples the least squares support vector regression (LSSVR) with the grey wolf optimization (GWO) to consider effectively the influencing factors and improve the predictive accuracy in predicting the foamed concrete’s compressive strength. Performance of the proposed model was evaluated using a real-world dataset. Comparison results confirm that the proposed GWO–LSSVR model was superior than the support vector regression, artificial neural networks, random forest, and M5Rules with the improvement rate of 144.2–284.0% in mean absolute percentage error (MAPE). Notably, the evaluation results show that the GWO–LSSVR model showed the good agreement between the actual and predicted values with the correlation coefficient of 0.991 and MAPE of 3.54%. Thus, the proposed AI model was suggested as an effective tool for designing foamed concrete materials.