Machine Learning-Based Predictive Modeling of Sustainable Lightweight Aggregate Concrete

Nowadays, lightweight aggregate concrete is becoming more popular due to its versatile properties. It mainly helps reduce the dead loads of structure, which ultimately reduces design load requirements. The main challenge associated with finding an optimized mix per However, conventional material this composite quite costly, time-consuming, and iterative. This research proposes a simplified methodology for designing structural non-structural by incorporating machine learning. For purpose, five distinct learning algorithms, support vector (SVM), artificial neural network (ANN), decision tree (DT), Gaussian process regression (GPR), extreme gradient boosting (XGBoost) were investigated. training, testing, validation process, total 420 data points collected from 43 published journal articles. performance models was evaluated based on statistical indicators. Overall, 11 input parameters, including ingredients properties entertained; only output parameter compressive strength concrete. results revealed that GPR model outperformed remaining four attaining R2 value 0.99, RMSE 1.34, MSE 1.79, MAE 0.69. In nutshell, these modern techniques can be employed make easy without extensive experimentation.