×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerAccurate prediction of concrete compressive strength remains a critical challenge in structural engineering due to the complex, non-linear relationships between mixture components and mechanical properties. This study presents a comprehensive machine learning framework for predicting concrete compressive strength, incorporating both deterministic and probabilistic approaches. We analyzed 1030 laboratory-tested concrete specimens with eight input variables to evaluate four distinct algorithms: linear regression, support vector regression, random forest, and artificial neural networks. Additionally, we developed a Monte Carlo dropout neural network to quantify prediction uncertainty through Bayesian approximation. Results demonstrate that ensemble tree-based methods achieved superior predictive performance with a root mean square error of 5.47 MPa and coefficient of determination of 0.884, significantly outperforming conventional approaches at the 0.01 significance level. Feature importance analysis revealed that curing age and cement content collectively account for 66% of the predictive variance, while water content exhibits the expected negative correlation with strength development. However, uncertainty quantification through Monte Carlo dropout revealed systematic undercalibration, achieving only 38.4% coverage of the nominal 95% prediction interval. These findings provide engineers with quantitative insights for mixture design optimization while emphasizing the importance of uncertainty awareness in computational predictions for structural applications.
This paper offers a comprehensive review of column-based ground improvement techniques, focusing on their fundamental mechanisms, design principles, construction methods, and field applications. It highlights stone columns and deep soil mixing (DSM) as the most widely used and effective solutions for enhancing the performance of weak and compressible soils. The core principles, including stress redistribution, increased shear strength, and accelerated consolidation, are discussed in detail. The review synthesizes key design parameters such as column geometry, area replacement ratio, and the role of geosynthetic reinforcement and load transfer platforms. It also examines the practical application of these methods through various case studies on embankments, tank foundations, and excavation supports. A dedicated section explores the pivotal role of numerical modeling, especially the finite element method (FEM), and emerging AI-driven approaches like Physics-Informed Neural Networks (PINNs) and surrogate modeling, which are shown to improve predictive accuracy and optimize the design process. Furthermore, the paper addresses critical challenges and limitations, including material variability, installation uncertainties, environmental impacts, and the need for enhanced quality control and long-term monitoring. It concludes by outlining future trends and innovations, such as the adoption of sustainable materials and the integration of machine learning for predictive design and real-time monitoring. This synthesis provides a structured overview of current best practices and offers valuable insights into the future direction of this vital area of geotechnical engineering.