Physics-Guided Generative AI for Property-Targeted 3D Porous Media Design
2026-07-27 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors developed a new AI method to design complex 3D porous materials used in things like filters and batteries. Their approach combines several AI models that learn how to create materials with specific properties, like porosity and how fluids flow through them. By using physics knowledge, their method better matches these target properties compared to previous AI models. This work helps make designing advanced materials more efficient and accurate.
porous mediainverse designvariational autoencoderlatent diffusion modelporositypermeabilitygenerative AIdifferentiable surrogate model
Authors
Peng Wang
Abstract
Inverse design of three-dimensional porous media is central to applications in filtration, catalysis, energy storage, fuel cells, thermal management, and biomedical scaffolds, but remains challenging because many distinct pore geometries can share similar porosity or permeability while small structural changes can strongly affect transport behaviour. This paper proposes a physics-guided generative AI framework for property-targeted porous media design, combining a property-aware variational autoencoder, a conditional latent diffusion model, and an independently trained differentiable structure-to-property surrogate. The framework learns a compact, physically informative latent design space, generates porous structures conditioned on target porosity and directional permeability, and refines generated samples using property-level feedback during denoising and decoding. Experiments on procedurally generated structures and real micro-CT porous-media datasets show improved target-property matching, directional permeability control, and property correlation compared with representative property-aware variational-autoencoder and latent-diffusion baselines. The results demonstrate a scalable route towards controllable inverse design of complex porous geometries and establish a foundation for simulation-informed generative AI tools in engineering and advanced materials discovery.