Data Driven ExtraTrees-Based State-of-Charge Estimation for New and Aged Li-ion Battery Cells
Nayeemuddin MOHAMMED, Ala A. HUSSEIN, Hiren MEWADA
Abstract. The use of lithium-ion batteries is essential in modern life. They are used in the drive of medical equipment, transport, renewable energy, and backup power. Effective state-of-charge (SOC) regression is essential to the safety and performance of the lithium-ion (Li-ion) batteries. However, most commercial techniques are valid only when the battery is new. Also, methods based solely on current measurements are susceptible to cumulative error, which reduces the accuracy of the estimate. The accurate prediction of SOC is a serious engineering challenge because it cannot be directly measured at the battery terminals. The present paper proposes a SOC regression approach based on an ExtraTrees Classifier and a Long Short-Term Memory that operate on voltage and surface temperature as input parameters, thereby eliminating the need for current sensing. Training and testing of the model are performed using both new and old Li-ion cell data to assess its viability across different battery ages. Results indicate that SOC regression accuracy increases with battery age because higher internal resistance results in more distinct temperature rise patterns. The suggested technique is sufficient to explain such alterations and to provide valid predictions across different conditions. The R2 values are 96% and 99% for the ExtraTrees Classifier model in new and aged cells, respectively. This technique provides a scalable, practical approach to battery management systems for electric vehicles and stationary storage by using easy-to-measure indicators and eliminating current integration errors.
Keywords
Li-Ion Battery, State-of-Charge, Machine Learning, Electric Vehicles
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: Nayeemuddin MOHAMMED, Ala A. HUSSEIN, Hiren MEWADA, Data Driven ExtraTrees-Based State-of-Charge Estimation for New and Aged Li-ion Battery Cells, Materials Research Proceedings, Vol. 64, pp 447-454, 2026
DOI: https://doi.org/10.21741/9781644904091-56
The article was published as article 56 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] J. Tao, S. Wang, W. Cao, C. Fernandez, F. Blaabjerg, and L. Cheng, “An innovative multitask learning – Long short-term memory neural network for the online anti-aging state of charge estimation of lithium-ion batteries adaptive to varying temperature and current conditions,” Energy, vol. 314, p. 134272, Jan. 2025. https://doi.org/10.1016/j.energy.2024.134272
[2] Y. Miao, Y. Gao, X. Liu, Y. Liang, and L. Liu, “Analysis of State-of-Charge Estimation Methods for Li-Ion Batteries Considering Wide Temperature Range,” Energies, vol. 18, no. 5, p. 1188, Jan. 2025. https://doi.org/10.3390/en18051188
[3] I. M. Monirul, L. Qiu, and R. Ruby, “Accurate state of charge estimation for UAV-centric lithium-ion batteries using customized unscented Kalman filter,” Journal of Energy Storage, vol. 107, p. 114955, Jan. 2025. https://doi.org/10.1016/j.est.2024.114955
[4] Q. Xu et al., “An expansion force-based method for accurate state of charge estimation across the entire lifecycle of lithium-ion batteries,” Journal of Energy Storage, vol. 137, p. 118705, Nov. 2025. https://doi.org/10.1016/j.est.2025.118705
[5] Z. Huang, J. Zhu, Z. Wang, X. Zhang, and G. Fan, “A recovery model for battery data in the cloud and its application of state-of-charge estimation in electric vehicles,” Control Engineering Practice, vol. 165, p. 106579, Dec. 2025. https://doi.org/10.1016/j.conengprac.2025.106579
[6] O. Ozer and H. Arabaci, “State of Charge Estimation in Li-Ion Batteries Using a Parallel LSTM-Based Approach: The Impact of Modeling Based on Operating States,” IEEE Access, vol. 13, pp. 130719–130730, 2025. https://doi.org/10.1109/ACCESS.2025.3591970
[7] J. Zhou, J. Li, X. Wu, T. Liu, and Y. Jiang, “Multi-physics model-based filtering for simultaneous state of charge and core temperature estimation in lithium-ion batteries,” Journal of Energy Storage, vol. 137, p. 118518, Nov. 2025. https://doi.org/10.1016/j.est.2025.118518
[8] W. Yu, Y. Zheng, and S. Wang, “Data-driven state-of-charge estimation for lithium-ion batteries using variational inference,” IEEE Transactions on Circuits and Systems II: Express Briefs, pp. 1–1, 2025. https://doi.org/10.1109/TCSII.2025.3608185
[9] Y. Fan et al., “A physics-enhanced hybrid kolmogorov–arnold network with dynamic coupling for interpretable battery state-of-charge estimation,” Applied Energy, vol. 400, p. 126533, Dec. 2025. https://doi.org/10.1016/j.apenergy.2025.126533
[10] D. Velumani and A. Bansal, “Temperature estimation in a lithium-ion cell using a machine learning based approach,” Applied Thermal Engineering, vol. 270, p. 126201, July 2025. https://doi.org/10.1016/j.applthermaleng.2025.126201
[11] A. Haraz, K. Abualsaud, and A. M. Massoud, “Hybrid Tree-Based Machine Learning Models for State-of-Charge and Core Temperature Estimation in EV Batteries,” IEEE Access, vol. 13, pp. 129962–129976, 2025. https://doi.org/10.1109/ACCESS.2025.3591057.
[12] NASA, “Public battery ageing dataset,” [Online]. Available: https://data.nasa.gov/dataset/li-ion-battery-aging-datasets. Accessed: Oct. 10, 2025.
“”
