Porous materials are ubiquitously present in natural environments and engineering applications, where their pore structural characteristics serve as critical factors influencing functional performance. Consequently, quantitative characterization of porous structures have attracted multidisciplinary attention, providing theoretical support for aerospace engineering, electrochemical engineering, functional materials, and biochips. The rapid advancement of computational technologies has enabled digital reconstruction as effective tool for characterizing the microstructures of porous materials. Machine learning-based methodologies have established novel pathways for digital reconstruction of porous materials. Thus, a new structural generation method for porous materials is proposed based on diffusion model. By using the Bentheimer sandstone 2D slices from the digital rocks super-resolution dataset, the image generation is implemented through denoising diffusion models following data preprocessing. Both Fréchet Inception Distance (FID) and Learned Perceptual Image Patch Similarity (LPIPS) metrics are used to evaluate the generated porous images. The results demonstrate the superior performance of diffusion models in generating high-fidelity images, achieving FID and LPIPS scores of 284.6933 and 0.165 respectively. The generated porous images exhibit enhanced structural authenticity compared to conventional methods. The present model provide a comprehensive framework for structural reconstruction of porous materials.

Lida Zhang, Wanting Hu, Chenhao Li, Jiawen Cai, Lihong Zhu. A New Digital Reconstruction Method of Porous Materials Based on Diffusion Model. Academic Journal of Materials & Chemistry (2025), Vol. 6, Issue 2: 51-56. https://doi.org/10.25236/AJMC.2025.060207.

[1] Liu P, Chen G-F. Porous materials: processing and applications[M]. Oxford, UK: Elsevier, 2014.

[2] Guddati S, Kiran A S K, Leavy M, et al. Recent advancements in additive manufacturing technologies for porous material applications[J]. The International Journal of Advanced Manufacturing Technology, 2019, 105: 193-215.

[3] Ma Z C, He X H, Yan P C, et al. A fast and flexible algorithm for microstructure reconstruction combining simulated annealing and deep learning[J]. Computers and Geotechnics, 2023, 164: 105755. 

[4] Feng J X, Teng Q Z, He X H, et al. Accelerating multi-point statistics reconstruction method for porous media via deep learning[J]. Acta Materialia, 2018, 159: 296 - 308.

[5] Shan L, Liu C, Liu Y, et al. Rock CT Image Super-Resolution Using Residual Dual-Channel Attention Generative Adversarial Network[J]. Energies, 2022, 15(14): 5115.

[6] Wang Y, Rahman S S, Arns C H. Super resolution reconstruction of μ-CT image of rock sample using neighbour embedding algorithm[J]. Physica A: Statistical Mechanics and its Applications, 2018, 493: 177 - 188.

[7] Siavashi J, Najafi A, Ebadi M, et al. A CNN-based approach for upscaling multiphase flow in digital sandstones[J]. Fuel, 2022, 308: 122047.

[8] Goodfellow I, Pouget-Abadie J, Mirza M, et al, Warde-Farley D, Ozair S, et al. Generative adversarial nets[C]//Advances in Neural Information Processing Systems. Montreal: MIT Press, 2014: 2672-2680.

[9] Zha W, Li X, Xing Y, et al. Reconstruction of shale image based on Wasserstein Generative Adversarial Networks with gradient penalty[J]. Advances in Geo-Energy Research, 2020, 4(1): 107 - 114.

[10] Mosser L, Dubrule O, Blunt M J. Reconstruction of Three-Dimensional Porous Media Using Generative Adversarial Neural Networks[J]. Physical Review E, 2017, 96(4): 043309.

[11] Feng J, He X, Teng Q, et al. Accelerating multi-point statistics reconstruction method for porous media via deep learning[J]. Acta Materialia, 2018, 159: 296 - 308. ISSN 1359-6454.

[12] Feng J, He X, Teng Q, et al. Reconstruction of porous media from extremely limited information using conditional generative adversarial networks[J]. Physical Review E, 2019, 100(3): 033308.

[13] Shams R, Masihi M, Boozarjomehry R B, et al. Coupled generative adversarial and auto-encoder neural networks to reconstruct three-dimensional multi-scale porous media[J]. Journal of Petroleum Science and Engineering, 2020, 186: 106794. ISSN 0920-4105.

[14] Yang Y, Liu F, Yao J, et al. Multi-scale reconstruction of porous media from low-resolution core images using conditional generative adversarial networks[J]. Journal of Natural Gas Science and Engineering, 2022, 99: 104411.

[15] Xu R, Zhang D, Wang N. Uncertainty quantification and inverse modeling for subsurface flow in 3D heterogeneous formations using a theory-guided convolutional encoder-decoder network[J]. Journal of Hydrology, 2022, 613(Pt A): 128321.

[16] Feng J, Teng Q, Li B, et al. An end-to-end three-dimensional reconstruction framework of porous media from a single two-dimensional image based on deep learning[J]. Computer Methods in Applied Mechanics and Engineering, 2020, 368: 113043.

[17] Sohl-Dickstein J, Weiss E A, Maheswaranathan N, et al. Deep unsupervised learning using nonequilibrium thermodynamics[C]. International conference on machine learning. pmlr, 2015.

[18] Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models[J]. Journal of Machine Learning Research, 2020, 21(1): 1-68.

[19] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[EB/OL]. (2015-05-18)[2025-03-05]. https://arxiv.org/abs/1505.04597.

[20] Niu Z, Zhong G, Yu H. A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021, 452: 48 - 62.

[21] Wang Y D, Mostaghimi P, Armstrong R. A Super Resolution Dataset of Digital Rocks (DRSRD1): Sandstone and Carbonate[J]. Digital Rocks Portal, April 2019.