Utilizing Machine Learning to Predict the Charge Storage Capability of Lithium-Ion Battery Materials
DOI:
https://doi.org/10.18321/ectj1651Keywords:
Artificial Intelligence, Machine Learning, Li-ion battery, Charge Storage CapacityAbstract
With the increasing demand for high-performance batteries in applications such as electric vehicles and portable electronics, accurately predicting the charge storage capacity of battery materials is crucial for developing more efficient and reliable energy storage systems. Machine Learning (ML) and data-driven approaches, plays a vital role in enhancing our understanding of Li-ion battery performance, guiding materials design, optimizing system efficiency, and accelerating innovation in energy storage technologies. In this study, an ML-based approach was applied to a dataset of 2345 rechargeable Li-ion battery materials, obtained from the Materials Project online portal, to predict gravimetric charge storage capacity ─ a key parameter for energy storage capability. To model this relationship, three key independent features were selected: average operating voltage, gravimetric energy density, and charging stability. Given the nonlinear dependencies between these features and the target variable, an ensemble learning algorithm, Gradient Boosting Regression (GBR), was employed. The model exhibited high predictive accuracy, achieving an R² value of 0.99 on the test dataset with a Mean Squared Error (MSE) of 20.08 for target feature values. These results confirm the model’s effectiveness in capturing complex relationships within the battery materials dataset, demonstrating its reliability in predicting charge storage capacity with minimal error. The feature selection strategy emphasizes practical electrochemical properties, enhancing the model’s interpretability and relevance for battery material screening. Its low error metrics indicate strong generalizability, positioning it as a valuable tool for accelerating battery material discovery and optimizing performance. This study distinguishes itself by focusing on gravimetric charge storage capacity prediction using domain-relevant features and an ensemble learning approach, leveraging a large open-source dataset to achieve high predictive accuracy. This is crucial for energy storage capabilities, but it has been less frequently modeled directly in ML-driven battery studies.
References
(1) A.G. Olabi, Q. Abbas, P.A. Shinde, M.A. Abdelkareem, Rechargeable batteries: Technological advancement, challenges, current and emerging applications. Energy 266 (2023) 126408. Crossref DOI: https://doi.org/10.1016/j.energy.2022.126408
(2) S. Manzetti, F. Mariasiu, Electric vehicle battery technologies: From present state to future systems. Renew. Sustain. Energy Rev. 51 (2015) 1004–1012. Crossref DOI: https://doi.org/10.1016/j.rser.2015.07.010
(3) J. Wen, D. Zhao, C. Zhang, An overview of electricity powered vehicles: Lithium-ion battery energy storage density and energy conversion efficiency. Renew. Energy 162 (2020) 1629–1648. Crossref DOI: https://doi.org/10.1016/j.renene.2020.09.055
(4) Z. Huang, G. Du, Nickel-based batteries for medium- and large-scale energy storage, in: Advances in Batteries for Medium and Large-Scale Energy Storage, Elsevier, 2015, pp. 73–90. Crossref DOI: https://doi.org/10.1016/B978-1-78242-013-2.00004-2
(5) A. Ulvestad, A brief review of current lithium ion battery technology and potential solid state battery technologies, arXiv preprint arXiv:1803.04317 (2018).
(6) S. Sarmah, L. Lakhanlal, B.K. Kakati, D. Deka, Recent advancement in rechargeable battery technologies. Wiley Interdiscip. Rev.: Energy and Environ. 12 (2023) e461. Crossref DOI: https://doi.org/10.1002/wene.461
(7) I. Rakhimbek, N. Baikalov, A. Konarov, A. Mentbayeva, Y. Zhang, Z. Mansurov, M. Wakihara, Zh. Bakenov, Efficient Polysulfides Conversion Kinetics Enabled by Ni@CNF Interlayer for Lithium Sulfur Batteries. Eurasian Chem.-Technol. J. 25 (2023) 147–156. Crossref DOI: https://doi.org/10.18321/ectj1517
(8) L. Lu, X. Han, J. Li, J. Hua, M. Ouyang, A review on the key issues for lithium-ion battery management in electric vehicles. J. Power Sources 226 (2013) 272–288. Crossref DOI: https://doi.org/10.1016/j.jpowsour.2012.10.060
(9) Z. Wei, Q. He, Y. Zhao, Machine learning for battery research. J. Power Sources 549 (2022) 232125. Crossref DOI: https://doi.org/10.1016/j.jpowsour.2022.232125
(10) M.F. Ng, Y. Sun, Z.W. Seh, Machine learning-inspired battery material innovation. Energy Adv. 2 (2023) 449–464. Crossref DOI: https://doi.org/10.1039/D3YA00040K
(11) M. Aykol, P. Herring, A. Anapolsky, Machine learning for continuous innovation in battery technologies. Nat. Rev. Mater. 5 (2020) 725–727. Crossref DOI: https://doi.org/10.1038/s41578-020-0216-y
(12) C. Lv, X. Zhou, L. Zhong, C. Yan, M. Srinivasan, Z.W. Seh, C. Liu, H. Pan, S. Li, Y. Wen, et al., Machine learning: an advanced platform for materials development and state prediction in lithium-ion batteries. Adv. Mater. 34 (2022) 2101474. Crossref DOI: https://doi.org/10.1002/adma.202101474
(13) N. Badi, A.R. Erra, F.C. Robles Hernandez, A.O. Okonkwo, M. Hobosyan, K.S. Martirosyan, Low-cost carbon-silicon nanocomposite anodes for lithium ion batteries. Nanoscale Res. Lett. 9 (2014) 1–8. Crossref DOI: https://doi.org/10.1186/1556-276X-9-360
(14) K. Sawai, T. Ohzuku, Factors affecting rate capability of graphite electrodes for lithium-ion batteries. J. Electrochem. Soc. 150 (2003) A674. Crossref DOI: https://doi.org/10.1149/1.1568107
(15) Q. Pang, X. Liang, A. Shyamsunder, L.F. Nazar, An in vivo formed solid electrolyte surface layer enables stable plating of li metal. Joule 1 (2017) 871–886. Crossref DOI: https://doi.org/10.1016/j.joule.2017.11.009
(16) Y.Y. Mamyrbaeva, M.A. Hobosyan, S.E. Kumekov, K.S. Martirosyan, Preparation of lithium cobaltate and electrochemical features for cathode battery materials. Int. J. SHS 23 (2014) 1–8. Crossref DOI: https://doi.org/10.3103/S1061386214010087
(17) Y. Zhang, L. Tao, C. Xie, D. Wang, Y. Zou, R. Chen, Y. Wang, C. Jia, S. Wang, Defect engineering on electrode materials for rechargeable batteries. Adv. Mater. 32 (2020) 1905923. Crossref DOI: https://doi.org/10.1002/adma.201905923
(18) D.-W. Chung, P.R. Shearing, N.P. Brandon, S.J. Harris, R.E. Garcia, Particle size polydispersity in li-ion batteries. J. Electrochem. Soc. 161 (2014) A422. Crossref DOI: https://doi.org/10.1149/2.097403jes
(19) J.M. Bhatt, Effect of Temperature on Battery Life and Performance in Electric Vehicle, Int. J. Sci. Res. 2 (10) (2013). DOI: https://doi.org/10.15373/22778179/OCT2013/43
(20) J. Li, E. Murphy, J. Winnick, P.A. Kohl, Studies on the cycle life of commercial lithium ion batteries during rapid charge–discharge cycling. J. Power Sources 102 (2001) 294–301. Crossref DOI: https://doi.org/10.1016/S0378-7753(01)00821-7
(21) A. Valizadeh, M.H. Amirhosseini, Machine Learning in Lithium-Ion Battery: Applications, Challenges, and Future Trends. SN Comput. Sci. 5 (2024) 717. Crossref DOI: https://doi.org/10.1007/s42979-024-03046-2
(22) D. Cheng, W. Sha, L. Wang, et al., Solid-state Lithium Battery Cycle Life Prediction using machine learning. Appl. Sci. 11 (2021) 4671. Crossref DOI: https://doi.org/10.3390/app11104671
(23) P. Sharma, B.J. Bora, A Review of Modern Machine Learning Techniques in the Prediction of Remaining Useful Life of Lithium-Ion Batteries. Batteries 9 (2022) 13. Crossref DOI: https://doi.org/10.3390/batteries9010013
(24) K. Schofer, F. Laufer, J. Stadler, et al., Machine learning-based lifetime prediction of Lithium-Ion cells. Adv. Sci. 9 (2022) 2200630. Crossref DOI: https://doi.org/10.1002/advs.202200630
(25) M.K. Tran, S. Panchal, V. Chauhan, N. Brahmbhatt, A. Mevawalla, R. Fraser, M. Fowler, Python-based scikit-learn machine learning models for thermal and electrical performance prediction of high capacity lithium-ion battery. Int. J. Energy Res. 46 (2022) 786–794. Crossref DOI: https://doi.org/10.1002/er.7202
(26) P. Fermín-Cueto, E. McTurk, M. Allerhand, et al., Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells. Energy and AI 1 (2020) 100006. Crossref DOI: https://doi.org/10.1016/j.egyai.2020.100006
(27) Y. Zhang, Y.-F. Li, Prognostics and health management of lithium-ion battery using deep learning methods: a review. Renew. Sustain. Energy Rev. 161 (2022) 112282. Crossref DOI: https://doi.org/10.1016/j.rser.2022.112282
(28) J. Zhao, X. Feng, Q. Pang, J. Wang, Y. Lian, M. Ouyang, A. F. Burke, Battery prognostics and health management from a machine learning perspective. J. Power Sources 581 (2023) 233474. Crossref DOI: https://doi.org/10.1016/j.jpowsour.2023.233474
(29) A. Thelen, X. Huan, N. Paulson, S. Onori, Z. Hu, C. Hu, Probabilistic machine learning for battery health diagnostics and prognostics-review and perspectives. npj Mater. Sustain. 2 (2024) 14. Crossref DOI: https://doi.org/10.1038/s44296-024-00011-1
(30) S.-A. Amamra, Random Forest-Based Machine Learning Model Design for 21,700/5 Ah Lithium Cell Health Prediction Using Experimental Data, Physchem, 5 (2025) 12. Crossref DOI: https://doi.org/10.3390/physchem5010012
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Manoj Chhetri, Karen S. Martirosyan
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to: Share — copy and redistribute the material in any medium or format. Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Eurasian Chemico-Technological Journal applies a Creative Commons Attribution 4.0 International License to articles and other works we publish.
Subject to the acceptance of the Article for publication in the Eurasian Chemico-Technological Journal, the Author(s) agrees to grant Eurasian Chemico-Technological Journal permission to publish the unpublished and original Article and all associated supplemental material under the Creative Commons Attribution 4.0 International license (CC BY 4.0).
Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.
