Predicting the 3D microstructure of SOFC anodes from 2D SEM images using stochastic microstructure modeling and CNNs
Source abstract
Abstract
Abstract The 3D microstructure of solid oxide fuel cell anodes significantly influences their electrochemical performance, but conventional methods for acquiring high-resolution microstructural 3D data, such as focused ion beam scanning electron microscopy, are costly in both time and resources. In contrast, obtaining 2D images, such as from scanning electron microscopy (SEM), is more accessible, though typically providing insufficient information to accurately characterize the 3D microstructure. To address this challenge, we propose a novel approach that predicts the 3D microstructure from 2D SEM images. The presented method utilizes a low-parametric stochastic geometry model to generate virtual 3D microstructures and employs a physics-based SEM simulation tool to obtain the corresponding 2D SEM images. By systematically varying the model parameters, a large dataset can be generated to train convolutional neural networks. By doing so, we can statistically reconstruct the 3D microstructure from 2D SEM images by drawing realizations from the stochastic 3D model using the predicted model parameters. This workflow is quantitatively validated by an error analysis on geometrical descriptors, which shows that 3D microstructures can be predicted with reasonably high accuracy from 2D SEM images. Thus, this approach is a valuable computational tool that additionally circumvents the typically time-consuming segmentation of image data.
Source: crossref · Quality: baseline
Research context
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (66)
Show source-provided references
1. Brandon, N., Ruiz-Trejo, E. & Boldrin, P. Solid Oxide Fuel Cell Lifetime and Reliability: Critical Challenges in Fuel Cells (Academic Press, 2017).
2. Fergus, J., Hui, R., Li, X., Wilkinson, D. P. & Zhang, J. Solid Oxide Fuel Cells: Materials Properties and Performance (CRC Press, 2016).10.1201/9781420088847 ↗
3. Mendonça, C., Ferreira, A. & Santos, D. M. F. Towards the commercialization of solid oxide fuel cells: recent advances in materials and integration strategies. Fuels 2, 393–419 (2021).10.3390/fuels2040023 ↗
4. Le, D.-D., Nguyen, H.-L., Yu, S., Le, H. H. & Hoang, T.-D. Progress and outlook of solid oxide fuel cell technology for stationary power generation applications. Front. Energy Res. 13, 1650696 (2025).10.3389/fenrg.2025.1650696 ↗
5. Baldi, F., Wang, L., Pérez-Fortes, M. & Maréchal, F. A cogeneration system based on solid oxide and proton exchange membrane fuel cells with hybrid storage for off-grid applications. Front. Energy Res. 6, 139 (2019).10.3389/fenrg.2018.00139 ↗
6. Wu, Z. et al. A comprehensive review of modeling of solid oxide fuel cells: from large systems to fine electrodes. Chem. Rev. 125, 2184–2268 (2025).10.1021/acs.chemrev.4c00614 ↗
7. Bischof, C. et al. Microstructure optimization of nickel/gadolinium-doped ceria anodes as key to significantly increasing power density of metal-supported solid oxide fuel cells. Int. J. Hydrog. Energy 44, 31475–31487 (2019).10.1016/j.ijhydene.2019.10.010 ↗
8. Sciazko, A. et al. Influence of initial powder morphology on polarization characteristics of nickel/gadolinium-doped-ceria solid oxide fuel cells electrode. J. Electrochem. Soc. 166, F44 (2019).10.1149/2.0181902jes ↗
9. Sciazko, A., Yokoi, R., Komatsu, Y., Shimura, T. & Shikazono, N. Evaluation of strontium doped lanthanum chromium manganite (LSCM) and gadolinium doped ceria (GDC) anode with different compositions. ECS Trans. 91, 1711 (2019).10.1149/09101.1711ecst ↗
10. Hussain, S. & Yangping, L. Review of solid oxide fuel cell materials: cathode, anode, and electrolyte. Energy Transit. 4, 113–126 (2020).10.1007/s41825-020-00029-8 ↗
11. Eguchi, K., Setoguchi, T., Inoue, T. & Arai, H. Electrical properties of ceria-based oxides and their application to solid oxide fuel cells. Solid State Ion. 52, 165–172 (1992).10.1016/0167-2738(92)90102-U ↗
12. Kubota, J. et al. Self-modification of Ni metal surfaces with CeO2 to suppress carbon deposition at solid oxide fuel cell anodes. Fuel Cells 17, 402–406 (2017).10.1002/fuce.201600180 ↗
13. Zhang, L., He, H. Q., Chen, X., Ma, J. & Song, X. C. A comparative study of H2S poisoning on electrode behavior of Ni/YSZ and Ni/GDC anodes of solid oxide fuel cells. Int. J. Hydrog. Energy 35, 12359–12368 (2010).10.1016/j.ijhydene.2010.08.067 ↗
14. Lee, J.-H. et al. The impact of anode microstructure on the power generating characteristics of SOFC. Solid State Ion. 158, 225–232 (2003).10.1016/S0167-2738(02)00915-3 ↗
15. Banhart, J. Advanced Tomographic Methods in Materials Research and Engineering (Oxford University Press, 2008).10.1093/acprof:oso/9780199213245.001.0001 ↗
16. Mosser, L., Dubrule, O. & Blunt, M. J. Reconstruction of three-dimensional porous media using generative adversarial neural networks. Phys. Rev. E 96, 043309 (2017).10.1103/PhysRevE.96.043309 ↗
17. Gayon-Lombardo, A., Mosser, L., Brandon, N. P. & Cooper, S. J. Pores for thought: generative adversarial networks for stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries. npj Comput. Mater. 6, 82 (2020).10.1038/s41524-020-0340-7 ↗
18. Kench, S. & Cooper, S. J. Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion. Nat. Mach. Intell. 3, 299–305 (2021).10.1038/s42256-021-00322-1 ↗
19. Li, X. et al. 3D microstructure reconstruction and characterization of porous materials using a cross-sectional SEM image and deep learning. Heliyon 10, e39185 (2024).10.1016/j.heliyon.2024.e39185 ↗
20. Seibert, P., Raçloff, A., Ambati, M. & Kästner, M. Descriptor-based reconstruction of three-dimensional microstructures through gradient-based optimization. Acta Mater. 227, 117667 (2022).10.1016/j.actamat.2022.117667 ↗
21. Seibert, P., Raçloff, A., Kalina, K. & Kästner, M. Fast descriptor-based 2D and 3D microstructure reconstruction using the Portilla-Simoncelli algorithm. Eng. Comput. 41, 589–607 (2025).10.1007/s00366-024-02026-7 ↗
22. Seibert, P., Raçloff, A., Kalina, K., Ambati, M. & Kästner, M. Microstructure characterization and reconstruction in Python: MCRpy. Integr. Mater. Manuf. Innov. 11, 450–466 (2022).10.1007/s40192-022-00273-4 ↗
23. Langner, E., Seibert, P., Semenov, A., Kästner, M. & Wallmersperger, T. Structure-property relationships of solid oxide fuel cell electrodes using real and reconstructed microstructures. Int. J. Numer. Methods Eng. 126, e70205 (2025).10.1002/nme.70205 ↗
24. van Kessel, L. C. P. M. & Hagen, C. W. Nebula: Monte Carlo simulator of electron-matter interaction. SoftwareX 12, 100605 (2020).10.1016/j.softx.2020.100605 ↗
25. Schröder, L. F., Weber, S., Fuchs, L., Schmidt, V. & Prifling, B. Data from: predicting the 3D microstructure of SOFC anodes from 2D SEM images using stochastic microstructure modeling and CNNs. https://doi.org/10.5281/zenodo.19555367 (2026).10.5281/zenodo.19555367 ↗
26. Müller, S. et al. Deep learning-based segmentation of lithium-ion battery microstructures enhanced by artificially generated electrodes. Nat. Commun. 12, 6205 (2021).10.1038/s41467-021-26480-9 ↗
27. Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In Proc. International Conference on Learning Representations (ICLR 2015).
28. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 770–778 (IEEE, 2016).10.1109/CVPR.2016.90 ↗
29. Howard, A. et al. Searching for MobileNetV3. In Proc. IEEE/CVF International Conference on Computer Vision, 1314–1324 (IEEE, 2019).10.1109/ICCV.2019.00140 ↗
30. Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. In Proc. International Conference on Learning Representations (2021).
31. Weber, S. et al. A time-continuous approach to analyzing anode aging in solid-oxide fuel cells via stochastic 3D microstructure modeling and physics-based simulations. Comput. Mater. Sci. 264, 114491 (2026).10.1016/j.commatsci.2026.114491 ↗
32. Chiu, S. N., Stoyan, D., Kendall, W. S. & Mecke, J. Stochastic Geometry and its Applications 3rd edn (John Wiley & Sons, 2013).10.1002/9781118658222 ↗
33. Molchanov, I. Theory of Random Sets 2nd edn (Springer, 2017).10.1007/978-1-4471-7349-6 ↗
34. Lantuéjoul, C. Geostatistical Simulation: Models and Algorithms (Springer, 2013).
35. Lang, A. & Potthoff, J. Fast simulation of Gaussian random fields. Monte Carlo Methods Appl. 17, https://www.degruyter.com/document/doi/10.1515/mcma.2011.009/html (2011).10.1515/mcma.2011.009 ↗
36. Salvat, F., Jablonski, A. & Powell, C. J. ELSEPA - Dirac partial-wave calculation of elastic scattering of electrons and positrons by atoms, positive ions and molecules. Computer Phys. Commun. 165, 157–190 (2005).10.1016/j.cpc.2004.09.006 ↗
37. Kieft, E. & Bosch, E. Refinement of Monte Carlo simulations of electron-specimen interaction in low-voltage SEM. J. Phys. D Appl. Phys. 41, 215310 (2008).10.1088/0022-3727/41/21/215310 ↗
38. Penn, D. R. Electron mean-free-path calculations using a model dielectric function. Phys. Rev. B 35, 482 (1987).10.1103/PhysRevB.35.482 ↗
39. Weber, S. et al. Comparing the 3D morphology of solid-oxide fuel cell anodes for different manufacturing processes, annealing times, and operating temperatures. J. Electrochem. Soc. 172, 044506 (2025).10.1149/1945-7111/adc6c1 ↗
40. Sinsomboonthong, S. Performance comparison of new adjusted min-max with decimal scaling and statistical column normalization methods for artificial neural network classification. Int. J. Math. Math. Sci. 2022, 3584406 (2022).10.1155/2022/3584406 ↗
41. Wang, W. Principles of Machine Learning—The Three Perspectives (Springer, 2025).10.1007/978-981-97-5333-8 ↗
42. Shalev-Shwartz, S. & Ben-David, S. Understanding Machine Learning: From Theory to Algorithms (Cambridge University Press, 2014).10.1017/CBO9781107298019 ↗
43. Witten, I. H., Frank, E., Hall, M. A., Pal, C. J. & Foulds, J. R. Data Mining: Practical Machine Learning Tools and Techniques 5th edn (Morgan Kaufmann, 2025).
44. LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998).10.1109/5.726791 ↗
45. Hu, J., Shen, L. & Sun, G. Squeeze-and-excitation networks. In Proc. IEEE conference on Computer Vision and Pattern Recognition, 7132–7141 (IEEE, 2018).10.1109/CVPR.2018.00745 ↗
46. Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, 448–456 (PMLR, 2015).
47. Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. In Proc. 3rd International Conference on Learning Representations (ICLR, San Diego, CA, USA, 2015).
48. Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, Vol 32, 8024–8035 (Curran Associates, Inc., 2019)
49. Prifling, B. et al. Stochastic 3D microstructure modeling of anodes in lithium-ion batteries with a particular focus on local heterogeneity. Comput. Mater. Sci. 192, 110354 (2021).10.1016/j.commatsci.2021.110354 ↗
50. Gräfensteiner, P. et al. Data-driven stochastic 3D modeling of the nanoporous binder-conductive additive phase in battery cathodes. J. Math. Ind. 15, 9 (2025).10.1186/s13362-025-00174-z ↗
51. Prifling, B. et al. Parametric microstructure modeling of compressed cathode materials for Li-ion batteries. Comput. Mater. Sci. 169, 109083 (2019).10.1016/j.commatsci.2019.109083 ↗
52. Altendorf, H. & Jeulin, D. Random-walk-based stochastic modeling of three-dimensional fiber systems. Phys. Rev. E 83, 041804 (2011).10.1103/PhysRevE.83.041804 ↗
53. Townsend, P. et al. Stochastic modelling of 3D fiber structures imaged with X-ray microtomography. Comput. Mater. Sci. 194, 110433 (2021).10.1016/j.commatsci.2021.110433 ↗
54. Geiçendörfer, M., Liebscher, A., Proppe, C., Redenbach, C. & Schwarzer, D. Stochastic multiscale modeling of metal foams. Probabilistic Eng. Mech. 37, 132–137 (2014).10.1016/j.probengmech.2014.06.006 ↗
55. Westhoff, D. et al. Investigation of the relationship between morphology and permeability for open-cell foams using virtual materials testing. Mater. Des. 147, 1–10 (2018).10.1016/j.matdes.2018.03.022 ↗
56. Prifling, B., Röding, M., Townsend, P., Neumann, M. & Schmidt, V. Large-scale statistical learning for mass transport prediction in porous materials using 90,000 artificially generated microstructures. Front. Mater. 8, 786502 (2021).10.3389/fmats.2021.786502 ↗
57. Zhang, X. et al. Analysing tortuosity for solid oxide fuel cell anode material: experiments and modeling. J. Electrochem. Soc. 170, 094502 (2023).10.1149/1945-7111/acf884 ↗
58. Schladitz, K., Ohser, J. & Nagel, W. Measuring intrinsic volumes in digital 3D images. In 13th International Conference Discrete Geometry for Computer Imagery (eds Kuba, A., Nyúl, L. & Palágyi, K.) 247–258 (Springer, Berlin, 2007).10.1007/11907350_21 ↗
59. Thulasiraman, K. & Swamy, M. N. S. Graphs: Theory and Algorithms (John Wiley & Sons, 2011).
60. Holzer, L. et al. Tortuosity and Microstructure Effects in Porous Media: Classical Theories, Empirical Data and Modern Methods (Springer, 2023).10.1007/978-3-031-30477-4 ↗
61. Torquato, S. Random Heterogeneous Materials—Microstructure and Macroscopic Properties (Springer, 2002).10.1007/978-1-4757-6355-3 ↗
62. Cooper, S. J., Bertei, A., Shearing, P. R., Kilner, J. A. & Brandon, N. P. TauFactor: an open-source application for calculating tortuosity factors from tomographic data. SoftwareX 5, 203–210 (2016).10.1016/j.softx.2016.09.002 ↗
63. Greenwood, N. N. & Earnshaw, A. Chemistry of the Elements 2nd edn (Elsevier Butterworth-Heinemann, 2012).
64. Mishra, T. P. Electric Field Assisted Sintering of Gadolinium-doped Ceria. Ph.D. thesis, Ruhr-Universität Bochum (2019). Published in: Schriften des Forschungszentrums Jülich, Reihe Energie & Umwelt, Band 509.
65. Arblaster, J. W. Selected Values of the Crystallographic Properties of Elements (ASM International, 2018).
66. Sistla, S. K. et al. Electric field-assisted sintering of gadolinium-doped ceria: sintering and grain growth kinetics. J. Ceram. Sci. Technol. 11, 17–26 (2019).