Graded Porosity

Graded porosity, the variation of pore size and distribution within a material, is a key characteristic influencing diverse properties like diffusion, mechanical strength, and fluid flow. Current research heavily utilizes deep learning, particularly convolutional neural networks (CNNs) and variations like U-Nets and Vision Transformers, to predict and map porosity from various data sources, including thermal images, X-ray micro-computed tomography (µCT) scans, and seismic data. These advancements enable more efficient and accurate characterization of porous materials across diverse fields, from additive manufacturing and materials science to reservoir modeling and geophysics, ultimately improving material design and process optimization.