Spatial correlation and pore morphology analysis of limestone calcined clay cement (LC3) via machine learning and image-based characterisation

Comprehending the microstructure of LC3 is of paramount importance since it governs majority properties of cement. Here, we investigate the spatial correlation and pore morphology of LC3, revealing microstructural refinement effects through deep learning and image-based characterisation. A deep learning model was devel-oped to characterise the spatial correlation of the local features of 28-day LC3 with optimised resolution and physical image size, identifying a lower probability of connected pores occurring but a higher likelihood of connected solid particles in LC3 than in OPC. A 33% lower maximum correlation revealed by two-point corre-lation analysis inferred that LC3 possessed a smaller RVE size and increased packing density. The pore morphological analysis based on BSE images indicated a higher hydration rate and pore deformation in LC3. These findings demonstrate the microstructural refinement mechanisms of LC3 but also lay the foundation for localised microstructural characterisation of cementitious materials with the potential to complement existing traditional analyses.

Automated summary

Understanding the microstructure of LC3 is crucial for controlling cement properties. This study employs deep learning and image-based characterisation to investigate the spatial correlation and pore morphology of LC3, revealing its microstructural refinement effects. The findings highlight the lower probability of connected pores but higher likelihood of connected solid particles in LC3 compared to OPC, as well as a smaller RVE size and increased packing density. The analysis also demonstrates a higher hydration rate and pore deformation in LC3. These results provide insights into the microstructural mechanisms of LC3 and offer a foundation for localised characterisation of cementitious materials.