Machine Learning-Enabled Quantification and Interpretation of Structural Symmetry Collapse in Cementitious Materials

The mechanical and durability performance of cementitious materials is fundamentally governed by the symmetry, anisotropy, and hierarchical organization of their microstructures. Conventional experimental characterization—based on imaging, spectroscopy, and physical testing—often struggles to capture these multiscale spatial patterns and their nonlinear correlations with macroscopic performance. Recent advances in machine learning (ML) provide unprecedented opportunities to interpret structural symmetry and anisotropy through data-driven analytics, computer vision, and physics-informed models. Furthermore, we summarize cases where symmetry-informed descriptors improve performance prediction accuracy in fiber- and nano-modified composites, demonstrating that ML-based symmetry analysis can substantially complement the limitations of conventional experimental-based characterization. We confirm that image-based models such as CNN and U-Net quantify the directionality and connectivity of pores and cracks, and that physically informative neural networks (PINNs) and heterogeneous data-based models enhance physical consistency and computational efficiency compared to conventional FEM and CFD. Finally, we present the conceptual and methodological foundation for developing AI-based microstructural symmetry analysis, aiming to go beyond simple prediction and establish a conceptual foundation for AI-driven cement design based on microstructure–performance causality.