Predicting the Splitting Tensile Strength of Recycled Aggregate Concrete Using Individual and Ensemble Machine Learning Approaches

The application of waste materials in concrete is gaining more popularity for sustainable development. adaptation this approach not only reduces the environmental risks but also fulfills requirement material. This study used novel algorithms machine learning (ML) to forecast splitting tensile strength (STS) containing recycled aggregate (RA). gene expression programming (GEP), artificial neural network (ANN), and bagging techniques were investigated selected database. Results reveal that precision level model accurate toward prediction STS RA-based as opposed GEP ANN models. high value (0.95) coefficient determination (R2) lesser values errors (MAE, MSE, RMSE) a clear indication model. Moreover, statistical checks k-fold cross-validation method incorporated confirm validity employed In addition, sensitivity analysis was carried out know contribution each parameter outcome. ML approaches anticipation concrete’s mechanical properties will benefit area civil engineering by saving time, effort, resources.