Pore segmentation in electron micrographs: A probabilistic approach by ensemble machine learning

In this study, an automatic method for segmenting pores in scanning electron microscopy images was developed. An ensemble of machine learning classifiers was combined with a fully connected conditional random field to obtain a spatial pore probability field. This field was then thresholded to produce coherent binary pore masks, and a confidence per pore C l was defined to quantify the reliability of the segmentation. The approach was demonstrated on a broad-ion-beam polished sample of the shaley facies of the Opalinus Clay. Accurate segmentation enabled the derivation of pore size distributions (PSD), pore morphologies, orientations, and spatial statistics. By using the median of C l per size range, a data-driven lower truncation limit for PSD fitting was established. The resulting microstructural metrics supported the interpretation of rock properties such as permeability. These results highlighted the method’s relevance for materials such as Opalinus Clay, which is investigated as a potential candidate for a host rock for nuclear waste storage. • Probabilistic ensemble with Conditional Random Field for pore segmentation in electron micrographs. • Pore-level probability fields enable uncertainty quantification and mask confidence estimation. • A new method addresses pore segmentation challenges in Opalinus Clay SEM data. • A confidence score C l provides a pore-wise measure of segmentation quality. • The method supports detection of segmentation errors through direct feedback per pore.