The digital transition incorporating material science and artificial intelligence (AI) paves the way for accelerated design guidelines on material and device level. Recently machine learning algorithms have taken a big leap in this context. Their utilization is far-reaching, e.g., for autonomous driving, natural language processing, or speech recognition devices. Recently data driven approaches have gained also high interest, particularly to accelerate material development. In this talk we review our recent work [1-3] on sophisticated characterization workflows developed for Si-based anode materials incorporating machine learning for improved image analysis. 

[1] Vorauer, T., Kumar, P., Berhaut, C.L. et al. Multi-scale quantification and modeling of aged nanostructured silicon-based composite anodes. Commun Chem 3, 141 (2020). https://doi.org/10.1038/s42004-020-00386-x
[2] Vorauer, T., Schöggl, J., Sanadhya, S.G. et al. Impact of solid-electrolyte interphase reformation on capacity loss in silicon-based lithium-ion batteries. Commun Mater 4, 44 (2023). https://doi.org/10.1038/s43246-023-00368-1
[3] Häusler, M., Stamati, O., Gammer, C. et al. Amorphous shear band formation in crystalline Si-anodes governs lithiation and capacity fading in Li-ion batteries. Commun Mater 5, 163 (2024). https://doi.org/10.1038/s43246-024-00599-w