Real-Time, Interpretable Diagnostics for Solid-State Batteries via Machine Learning on In Situ Impedance Spectra

Abstract

Electrochemical impedance spectroscopy (EIS) is highly sensitive to interfacial processes in solid-state batteries (SSBs) but can be difficult to interpret in real time. Here we pair in situ EIS with machine learning (ML) to create a lightweight, interpretable diagnostic framework. By encoding spectra into feature vectors and training tree-based multi-output regressors, we achieve real-time predictions of state of charge and cycle index with R² >0.99. Feature-importance analysis links dominant mid- and low-frequency responses to cathode and anode degradation, respectively. Remarkably, retraining on only five key features maintains sub-percent accuracy, enabling millisecond-scale, impedance-based monitoring suitable for embedded solid-state battery management systems.

References

[1] Y. Zheng, Y. Shen, J. Guo, et al., “Recent Advances in Solid-State Lithium Batteries Based on Anode Engineering,” Nano Research Energy 3, no. 3 (2024): e9120118, https://doi.org/10.26599/nre.2024.9120118.

[2] X. Yao, D. Liu, C. Wang, et al., “High-Energy All-Solid-State Lithium Batteries With Ultralong Cycle Life,” Nano Letters 16, no. 11 (2016): 7148–7154, https://doi.org/10.1021/acs.nanolett.6b03448.

[3] H. Song, K. Münch, X. Liu, et al., “All-Solid-State Li-S Batteries With Fast Solid-Solid Sulfur Reaction,” Nature 637, no. 8047 (2025): 846–853, https://doi.org/10.1038/s41586-024-08298-9.

[4] Y.-Y. Sun, F. Li, and P.-Y. Hou, “Research Progress on the Interfaces of Solid-State Lithium Metal Batteries,” Journal of Materials Chemistry A 9, no. 15 (2021): 9481–9505, https://doi.org/10.1039/d1ta00467k.

[5] P. Vadhva, J. Hu, M. J. Johnson, et al., “Electrochemical Impedance Spectroscopy for All-Solid-State Batteries: Theory, Methods and Future Outlook,” ChemElectroChem 8, no. 11 (2021): 1930–1947, https://doi.org/10.1002/celc.202100108.

[6] L. Zhang, Y. Dai, C. Li, et al., “Recent Advances in Electrochemical Impedance Spectroscopy for Solid-State Batteries,” Energy Storage Materials 69 (2024): 103378, https://doi.org/10.1016/j.ensm.2024.103378.

[7] C.-Y. Yu, J. Choi, J. Dunham, et al., “Time-Resolved Impedance Spectroscopy Analysis of Aging in Sulfide-Based All-Solid-State Battery Full-Cells Using Distribution of Relaxation Times Technique,” Journal of Power Sources 597 (2024): 234116, https://doi.org/10.1016/j.jpowsour.2024.234116.

[8] Y. J. Kim, H. Jeong, S. Nam, D. Shin, J.-H. Lee, and H. Kim, “Degradation Analysis During Fast Lifetime Cycling of Sulfide-Based All-Solid-State Li-Metal Batteries Using in Situ Electrochemical Impedance Spectroscopy,” Journal of Materials Chemistry A 13, no. 29 (2025): 23946–23956, https://doi.org/10.1039/d5ta02065d.

[9] Y. Xu, A. Liaw, R. P. Sheridan, and V. Svetnik, “Development and Evaluation of Conformal Prediction Methods for Quantitative Structure-Activity Relationship,” ACS Omega 9, no. 27 (2024): 29478–29490, https://doi.org/10.1021/acsomega.4c02017.

[10] Y. Qi, M. W. Swift, E. J. Fuller, and A. A. Talin, “Interface Potentials Inside Solid-State Batteries: Origins and Implications,” MRS Bulletin 48, no. 12 (2023): 1239–1246, https://doi.org/10.1557/s43577-023-00625-1.

RIGHTS & PERMISSIONS

2026 The Author(s). Battery Energy published by Xijing University and John Wiley & Sons Australia, Ltd.