Quantifying the phase assemblage in the hydrated cement paste by an interpretable and automatic EDS image analysis framework

Abstract

The Energy dispersive X-ray spectroscopy (EDS) data, characterized by high dimensionality, low resolution, and large scale, necessitates a robust characterization method that is both easy to understand and delicate to reveal the underlying information. Here, we present a practical and interpretable framework for quantitative EDS (QEDS) image analysis. To improve the quality of data, we employ sequential processing techniques including guided filter, linear enhancement, and super-pixel segmentation. For phase identification and classification, the dimensionality reduction algorithm Potential of heat-diffusion for affinity-based transition embedding (Phate) was integrated with cluster analysis algorithm Gaussian Mixture Model (GMM). This integration cleanly and clearly reveals typical data patterns such as linear progressions and local clusters, indicating the presence of phase evolution and representative phases. We expect that this QEDS image analysis offers an intuitive and visual way to quantify the phase assemblage in cementitious systems, thereby shifting the quantification process from expert knowledge-dominated “black boxes” into data structure-dominated “glass boxes”.