Characterization of porous membranes using artificial neural networks

Porous membranes have been utilized intensively in a wide range of fields due to their special characteristics and a rigorous characterization of their microstructures is crucial for understanding their properties and improving the performance for target applications. A promising method for the quantitative analysis of porous structures leverages the physics-based generation of porous structures at the pore scale, which can be validated against real experimental microstructures, followed by building the process-structure-property relationships with data-driven algorithms such as artificial neural networks. In this study, a Variational AutoEncoder (VAE) neural network model is used to characterize the 3D structural information of porous materials and to represent them with low-dimensional latent variables, which further model the structure-property relationship and solve the inverse problem of process-structure linkage combined with the Bayesian optimization method. Our methods provide a quantitative way to learn structural descriptors in an unsupervised manner which can characterize porous microstructures robustly.

Automated summary

Porous membranes are widely used and understanding their microstructures is crucial for improving their performance. A promising method for quantitative analysis is to generate porous structures at the pore scale and validate them against experimental microstructures, then establish process-structure-property relationships using data-driven algorithms. This study uses a Variational AutoEncoder (VAE) neural network model to characterize the 3D structural information of porous materials and solve the inverse problem of process-structure linkage. Our methods provide a robust and unsupervised way to learn structural descriptors for porous microstructures.