Comparative Analysis of Data-Driven Models for Lithium-Ion Battery SOH Estimation
Mayssae TOUTI, Badr BOUOULID IDRISSI
Abstract. The evaluation of lithium-ion battery State of Health (SOH) plays a key role in ensuring reliable operation and improving the long-term durability of energy storage systems. However, battery degradation is a complex, time-dependent process, making accurate prediction challenging. This paper presents a comparative analysis of three data-driven models Gated Recurrent Unit (GRU), Support Vector Regression (SVR), Long Short-Term Memory (LSTM) network for SOH estimation. The NASA B0005 dataset, which contains voltage, current, temperature, and capacity measurements from repeated charge–discharge cycles, was used for training and testing all three models. To select the most informative features, the Pearson correlation coefficient was applied to identify the indicators most strongly correlated with capacity degradation. The results indicate that the GRU model yields lower RMSE and MAPE values compared to LSTM and SVR, demonstrating the highest predictive accuracy. These findings suggest that recurrent architectures, particularly GRU, are effective at capturing the temporal patterns in battery behavior. Future studies will focus on hybrid modeling approaches to further enhance prediction accuracy and robustness.
Keywords
State of Health (SOH), Long Short-Term Memory (LSTM), Battery Management Systems (BMS), Lithium-ion battery, Machine Learning (ML), Support Vector Regression (SVR), Gated Recurrent Unit (GRU)
Published online 4/25/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Mayssae TOUTI, Badr BOUOULID IDRISSI, Comparative Analysis of Data-Driven Models for Lithium-Ion Battery SOH Estimation, Materials Research Proceedings, Vol. 64, pp 60-67, 2026
DOI: https://doi.org/10.21741/9781644904091-8
The article was published as article 8 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] K.R. Ngoy, V.T. Lukong, K.O. Yoro, J.B. Makambo, N.C. Chukwuati, C. Ibegbulam, … & T.C. Jen, Lithium-ion batteries and the future of sustainable energy: A comprehensive review, Renewable and Sustainable Energy Rev. 223 (2025) 115971.. https://doi.org/s://doi.org/10.1016/j.rser.2025.115971
[2] T. Rahman, T. Alharbi, Exploring lithium-Ion battery degradation: A concise review of critical factors, impacts, data-driven degradation estimation techniques, and sustainable directions for energy storage systems, Batteries 10(7) (2024) 220.. https://doi.org/s://doi.org/10.3390/batteries10070220
[3] A.S. Akram, M. Sohaib, W. Choi, SOH Estimation of Lithium-Ion Batteries Using Distribution of Relaxation Times Parameters and Long Short-Term Memory Model, Batteries 11(5) (2025) 183.. https://doi.org/s://doi.org/10.3390/batteries11050183
[4] K. Tang, B. Luo, D. Chen, C. Wang, L. Chen, F. Li, … & C. Wang, The State of Health Estimation of Lithium-Ion Batteries: A Review of Health Indicators, Estimation Methods, Development Trends and Challenges, World Electric Vehicle J. 16(8) (2025) 429.. https://doi.org/s://doi.org/10.3390/wevj16080429
[5] E. Kim, S. Jung, Battery State of Health Estimation Methods: Implementation and Comparison of 11 Algorithms, IEEE Access (2025).. https://doi.org/s://doi.org/10.1109/ACCESS.2025.3541631
[6] M. Li, W. Xu, S. Zhang, L. Liu, A. Hussain, E. Hu, … & Z. Chen, State of health estimation and battery management: a review of health indicators, models and machine learning, Materials 18(1) (2025) 145.. https://doi.org/s://doi.org/10.3390/ma18010145
[7] Z. Wang, G. Feng, D. Zhen, F. Gu, A. Ball, A review on online state of charge and state of health estimation for lithium-ion batteries in electric vehicles, Energy Rep. 7 (2021) 5141-5161.. https://doi.org/s://doi.org/10.1016/j.egyr.2021.08.113
[8] E.H. Bayoumi, M. De Santis, H. Awad, A Brief Overview of Modeling Estimation of State of Health for an Electric Vehicle’s Li-Ion Batteries, World Electric Vehicle J. 16(2) (2025).. https://doi.org/s://doi.org/10.3390/wevj16020073
[9] N. Mohanty, N.K. Goyal, V.A. Naikan, Hybrid machine learning models for improved state of health estimation of lithium-ion batteries in electric vehicles, Mater. Res. Proc. 49 (2025).. https://doi.org/s://doi.org/10.21741/9781644903438-5
[10] A. Aitio, D. Jöst, D.U. Sauer, D.A. Howey, Learning battery model parameter dynamics from data with recursive Gaussian process regression, J. Dyn. Syst. Meas. Control 147(3) (2025) 031010.. https://doi.org/s://doi.org/10.1115/1.4067771
[11] Y. Song, J. Lu, H. Zhang, G. Liu, SOC and SOH Prediction of Lithium‐Ion Batteries Based on LSTM-AUKF Joint Algorithm, Energy Sci. Eng. 13(1) (2025) 240-254.. https://doi.org/s://doi.org/10.1002/ese3.1992
[12] X. Cai, T. Liu, State of Health Prediction for Lithium-Ion Batteries Using Transformer-LSTM Fusion Model, Appl. Sci. 15(7) (2025) 3747.. https://doi.org/s://doi.org/10.3390/app15073747
[13] K. Li, X. Chen, Machine learning-based lithium battery state of health prediction research, Appl. Sci. 15(2) (2025) 516.. https://doi.org/s://doi.org/10.3390/app15020516
[14] L. Qian, L. Xuan, J. Chen, Battery SOH estimation based on decision tree and improved support vector machine regression algorithm, Front. Energy Res. 11 (2023) 1218580.. https://doi.org/s://doi.org/10.3389/fenrg.2023.1218580
[15] Z. Hou, W. Xu, G. Jia, J. Wang, M. Cai, Estimation of SOH of lithium-ion batteries based on PSO-Bi GRU-Attention network, J. Electrochem. Soc. 171(2) (2024) 020550.. https://doi.org/s://doi.org/10.1149/1945-7111/ad29c4
[16] C. Zhang, L. Luo, Z. Yang, S. Zhao, Y. He, X. Wang, H. Wang, Battery SOH estimation method based on gradual decreasing current, double correlation analysis and GRU, Green Energy Intell. Transp. 2(5) (2023) 100108.. https://doi.org/s://doi.org/10.1016/j.geits.2023.100108
[17] Z. Liu, J. Zhao, H. Wang, C. Yang, A new lithium-ion battery SOH estimation method based on an indirect enhanced health indicator and support vector regression in PHMs, Energies 13(4) (2020) 830.. https://doi.org/s://doi.org/10.3390/en13040830
[18] L. Zhang, T. Ji, S. Yu, G. Liu, Accurate prediction approach of SOH for lithium-ion batteries based on LSTM method, Batteries 9(3) (2023) 177.. https://doi.org/s://doi.org/10.3390/batteries9030177
[19] Y. He, N. Pattanadech, K. Sukemoke, M. Pan, L. Chen, The State of Health Estimation of Retired Lithium-Ion Batteries Using a Multi-Input Metabolic Gated Recurrent Unit, Energies 18(5) (2025).. https://doi.org/s://doi.org/10.3390/en18051035
