Assessment of compressive strength of eco-concrete reinforced using machine learning tools

Predicting the compressive strength of Compressed Earth Blocks (CEB) is a challenging task due to the nonlinear relationships among their diverse components, including cement, clay, sand, silt, and fibers. This study employed PyCaret, an automated machine learning platform, to address this complexity by developing and evaluating predictive models. The analysis demonstrated that fiber content exhibited a strong positive correlation with cement content, with a correlation coefficient of 0.9444, indicating a significant influence on compressive strength. Multiple machine learning algorithms were tested using metrics such as the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE) to assess model performance. Among these, the Extra Trees Regressor showed the best predictive capability with R² = 0.9444 (highly accurate predictions), RMSE = 0.4909 (low variability in prediction errors) and MAE = 0.1899 (minimal average prediction error). The results confirm that PyCaret effectively automates the machine learning workflow, enabling accurate modeling of complex material behavior. The Extra Trees Regressor outperformed other algorithms due to its ability to handle highly nonlinear and multivariate datasets, making it particularly well-suited for predicting the compressive strength of CEB. This approach offers a significant advantage over traditional laboratory testing, which is time-consuming and resource-intensive. By incorporating machine learning techniques, especially using PyCaret's streamlined processes, the prediction of CEB strength becomes more efficient and reliable, providing a practical tool for engineers and researchers in material science.