# Multiscale reconstruction of porous media based on multiple dictionaries learning

arXiv: https://arxiv.org/abs/2205.08278 · HTML: https://mlsanity.com/paper/2205.08278/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 54 references that are in the map.
- First posted on arXiv 16 May 2022.

## Builds on (most cited first, 3 of 3)

- [Reconstruction of three-dimensional porous media using generative adversarial neural networks](https://mlsanity.com/paper/1704.03225/) (2017)
- [A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions](https://mlsanity.com/paper/1805.02784/) (2018)
- [CT-image Super Resolution Using 3D Convolutional Neural Network](https://mlsanity.com/paper/1806.09074/) (2018)

## Abstract (arXiv)

Digital modeling of the microstructure is important for studying the physical and transport properties of porous media. Multiscale modeling for porous media can accurately characterize macro-pores and micro-pores in a large-FoV (field of view) high-resolution three-dimensional pore structure model. This paper proposes a multiscale reconstruction algorithm based on multiple dictionaries learning, in which edge patterns and micro-pore patterns from homology high-resolution pore structure are introduced into low-resolution pore structure to build a fine multiscale pore structure model. The qualitative and quantitative comparisons of the experimental results show that the results of multiscale reconstruction are similar to the real high-resolution pore structure in terms of complex pore geometry and pore surface morphology. The geometric, topological and permeability properties of multiscale reconstruction results are almost identical to those of the real high-resolution pore structures. The experiments also demonstrate the proposal algorithm is capable of multiscale reconstruction without regard to the size of the input. This work provides an effective method for fine multiscale modeling of porous media.