Enhancing model accuracy in lithium-ion battery crystal system development
-
Lin Wang
Abstract
One of the most significant contemporary energy storage technologies is lithium-ion batteries, and the performance and stability of such batteries are closely associated with the constituent minerals’ crystal structure. In this work, machine learning is applied for cattregorizing lithium-ion batteries into three major crystal systems: monoclinic, orthorhombic, and triclinic. The performance comparison of several machine learning models, namely Support Vector Classifiers, Nu-support Vector Classification, K-Nearest Neighbors, Adaptive Boosting, Extra Trees, and the optimized Extra Trees model, POA-ET, which is achieved via applying Pelican Optimization Algorithm, are considered in this investigation. Among those, the POA-ET emerges as the best and yields high performances in terms of several key metrics regarding the test and training data sets. The model’s reliability is further validated through further analysis, demonstrating its robustness and generalizability. Spacegroup, Nsites, and Volume respectively are the most important features according to feature importance analysis, significantly impacting the predictions. These results not only demonstrate the predictive capability of the machine learning models but also give insights into the factors underlying lithium-ion battery material performance. The presented work bridges computational modeling with practical applications and thus opens an avenue for creating high-performing lithium-ion batteries in order to aid in the world’s shift to sustainable and clean energy systems.
Acknowledgments
I would like to take this opportunity to acknowledge that there are no individuals or organizations that require acknowledgment for their contributions to this work.
-
Research ethics: Research involving Human Participants and Animals: The observational study conducted on medical staff needs no ethical code. Therefore, the above study was not required to acquire ethical code.
-
Informed consent: This option is not neccessary due to that the data were collected from the references.
-
Author contributions: The author contributed to the study’s conception and design. Data collection, simulation and analysis were performed by “Lin Wang”. Also the first draft of the manuscript was written by Lin Wang commented on previous versions of the manuscript.
-
Use of Large Language Models, AI and Machine Learning Tools: During the preparation of this work, the authors used Large Language Models, AI, and Machine Learning tools for tasks such as language refinement, data analysis, or figure generation, with all outputs being reviewed and validated by the authors to ensure accuracy and originality. After using these tools/services, the authors reviewed and edited the content and take full responsibility for the content of the published article.
-
Conflict of interest: The author declare no competing of interests.
-
Research funding: This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.
-
Data availability: The author do not have permissions to share data.
References
1. Kauwe, SK, Rhone, TD, Sparks, TD. Data-driven studies of Li-ion-battery materials. Crystals 2019;9:1–9. https://doi.org/10.3390/cryst9010054.Search in Google Scholar
2. Longo, RC, Xiong, K, Kc, S, Cho, K. Crystal structure and multicomponent effects in tetrahedral silicate cathode materials for rechargeable Li-ion batteries. Electrochim Acta 2014;121:434–42. https://doi.org/10.1016/j.electacta.2013.12.104.Search in Google Scholar
3. Zhang, T, Li, D, Tao, Z, Chen, J. Understanding electrode materials of rechargeable lithium batteries via DFT calculations. Prog Nat Sci:Mater Int 2013;23:256–72. https://doi.org/10.1016/j.pnsc.2013.04.005.Search in Google Scholar
4. Frank, J. Challenges and opportunities of layered cathodes of challenges and opportunities of layered cathodes of LiNixMnyCo(1-x-y)O2 for high-performance lithium-ion batteries LiNixMnyCo(1-x-y)O2 for high-performance lithium-ion batteries. [Online]. Available: https://scholarworks.uark.edu/meeguht.Search in Google Scholar
5. Liu, X, Li, K, Li, X. The electrochemical performance and applications of several popular lithium-ion batteries for electric vehicles - a review. In: Communications in computer and information science. Singapore: Springer Verlag; 2018:201–13 pp.10.1007/978-981-13-2381-2_19Search in Google Scholar
6. Wang, Y, Jiang, B. Attention mechanism-based neural network for prediction of battery cycle life in the presence of missing data. Batteries 2024;10:229. https://doi.org/10.3390/batteries10070229.Search in Google Scholar
7. Hautier, G, Fischer, C, Ehrlacher, V, Jain, A, Ceder, G. Data mined ionic substitutions for the discovery of new compounds. Inorg Chem 2011;50:656–63. https://doi.org/10.1021/ic102031h.Search in Google Scholar PubMed
8. Zeng, C, Zheng, R, Fan, F, Wang, X, Tian, G, Liu, S, et al.. Phase compatible surface engineering to boost the cycling stability of single-crystalline Ni-rich cathode for high energy density lithium-ion batteries. Energy Storage Mater 2024;72:103788. https://doi.org/10.1016/j.ensm.2024.103788.Search in Google Scholar
9. Fan, F, Zheng, R, Zeng, T, Xu, H, Wen, X, Wang, X, et al.. Cation-ordered Ni-rich positive electrode material with superior chemical and structural stability enabled by atomic substitution for lithium-ion batteries. Chem Eng J 2023;477:147181. https://doi.org/10.1016/j.cej.2023.147181.Search in Google Scholar
10. Premasudha, M, Srinivasulu Reddy, BR, Cho, K-K, Hyo-Jun, A, Sung, J-K, Subba Reddy, NG. Classification of the crystal structures of orthosilicate cathode materials for Li-ion batteries by artificial neural networks. Batteries 2024;11:13. https://doi.org/10.3390/batteries11010013.Search in Google Scholar
11. Houchins, G, Viswanathan, V. An accurate machine-learning calculator for optimization of Li-ion battery cathodes. J Chem Phys 2020;153:054124. https://doi.org/10.1063/5.0015872.Search in Google Scholar PubMed
12. Liu, Y, Guo, B, Zou, X, Li, Y, Shi, S. Machine learning assisted materials design and discovery for rechargeable batteries. Energy Storage Mater 2020;31:434–50. https://doi.org/10.1016/j.ensm.2020.06.033.Search in Google Scholar
13. Lv, C, Zhou, X, Zhong, L, Yan, C, Srinivasan, M, Seh, ZW, et al.. Machine learning: an advanced platform for materials development and state prediction in lithium‐ion batteries. Adv Mater 2022;34:2101474. https://doi.org/10.1002/adma.202101474.Search in Google Scholar PubMed
14. Prosini, PP. Crystal group prediction for lithiated manganese oxides using machine learning. Batteries 2023;9:112. https://doi.org/10.3390/batteries9020112.Search in Google Scholar
15. Yin, Y, Xu, G, Xie, Y, Luo, Y, Wei, Z, Li, Z. Utilizing deep learning for crystal system classification in lithium - ion batteries. J Theory Pract Eng Sci 2024;4:199–206. https://doi.org/10.53469/jtpes.2024.04(03).19.Search in Google Scholar
16. Attarian Shandiz, M, Gauvin, R. Application of machine learning methods for the prediction of crystal system of cathode materials in lithium-ion batteries. Comput Mater Sci 2016;117:270–8. https://doi.org/10.1016/j.commatsci.2016.02.021.Search in Google Scholar
17. Sahu, B, Panigrahi, A, Pati, A, Das, MN, Jain, P, Sahoo, G, et al.. Novel hybrid feature selection using binary portia spider optimization algorithm and fast mRMR. Bioengineering 2025;12:291. https://doi.org/10.3390/bioengineering12030291.Search in Google Scholar PubMed PubMed Central
18. Panda, P, Bisoy, SK, Panigrahi, A, Pati, A, Sahu, B, Guo, Z, et al.. BIMSSA: enhancing cancer prediction with salp swarm optimization and ensemble machine learning approaches. Front Genet 2025;15:1491602. https://doi.org/10.3389/fgene.2024.1491602.Search in Google Scholar PubMed PubMed Central
19. Houkan, A, Sahoo, AK, Gochhayat, SP, Sahoo, PK, Liu, H, Khalid, SG, et al.. Enhancing security in industrial IoT networks: machine learning solutions for feature selection and reduction. IEEE Access 2024;12:160864. https://doi.org/10.1109/access.2024.3481459.Search in Google Scholar
20. Prakash, K, Valeti, NJ, Jain, P, Pathak, CS, Singha, MK, Gupta, S, et al.. Single-crystal perovskite halide: crystal growth to devices applications. Energy Technol 2024;13:2400618. https://doi.org/10.1002/ente.202400618.Search in Google Scholar
21. Anđelić, N, Baressi Šegota, S. An advanced methodology for crystal system detection in Li-ion batteries. Electronics 2024;13:2278. https://doi.org/10.3390/electronics13122278.Search in Google Scholar
22. Bhavsar, H, Panchal, MH. A review on support vector machine for data classification. Int J Adv Res Comput Sci Eng Tech 2012;1:185–9.Search in Google Scholar
23. Liu, T, Jin, L, Zhong, C, Xue, F. Study of thermal sensation prediction model based on support vector classification (SVC) algorithm with data preprocessing. J Build Eng 2022;48:103919. https://doi.org/10.1016/j.jobe.2021.103919.Search in Google Scholar
24. Gunn, S. Support vector machines for classification and regression. ISIS Technical Report; 1997:1–42 pp.Search in Google Scholar
25. Vapnik, V, Golowich, S, Smola, A. Support vector method for function approximation, regression estimation and signal processing. Adv Neural Inf Process Syst 1996;9:281–7.Search in Google Scholar
26. Chew, HG, Bogner, RE, Lim, CC. Dual ν-support vector machine with error rate and training size biasing. In: ICASSP, IEEE international conference on acoustics, speech and signal processing - Proceedings. Institute of Electrical and Electronics Engineers Inc.; 2001:1269–72 pp.Search in Google Scholar
27. Gu, B, Wang, JD, Zheng, GS, Yu, YC. Regularization path for ν-support vector classification. IEEE Trans Neural Networks Learn Syst 2012;23:800–11. https://doi.org/10.1109/TNNLS.2012.2183644.Search in Google Scholar PubMed
28. Schölkopf, B, Smola, AJ, Williamson, RC, Bartlett, PL. New support vector algorithms. Neural Comput 2000;12:1207–45. https://doi.org/10.1162/089976600300015565.Search in Google Scholar PubMed
29. Steinbach, M, Tan, P-N. kNN: k-nearest neighbors. In: The top ten algorithms in data mining. Boca Raton, FL: Chapman and Hall/CRC; 2009:165–76 pp.10.1201/9781420089653-15Search in Google Scholar
30. Peterson, LE. K-nearest neighbor. Scholarpedia 2009;4:1883. https://doi.org/10.4249/scholarpedia.1883.Search in Google Scholar
31. Zhang, Z. Introduction to machine learning: k-nearest neighbors. Ann Transl Med 2016;4:218. https://doi.org/10.21037/atm.2016.03.37.Search in Google Scholar PubMed PubMed Central
32. Fix, E, Hodges, JL. Discriminatory analysis, nonparametric discrimination. Hoboken, NJ: International Statistical Review, Wiley-Blackwell; 1951.10.1037/e471672008-001Search in Google Scholar
33. Ferreira, A, Figueiredo, M. Ensemble machine learning, Zhang, C, Ma, Y, editors. New York, NY: Springer; 2012:35–85 pp.10.1007/978-1-4419-9326-7_2Search in Google Scholar
34. Schwenk, H, Bengio, Y. Training methods for adaptive boosting of neural networks. In: Advances in neural information processing systems 10 (NIPS 1997). Cambridge, MA: The MIT Press; 1997:647–50 pp.Search in Google Scholar
35. Freund, Y, Schapire, RE. A desicion-theoretic generalization of on-line learning and an application to boosting. In: European conference on computational learning theory. Springer; 1995:23–37 pp.10.1007/3-540-59119-2_166Search in Google Scholar
36. Saeed, U, Jan, SU, Lee, Y-D, Koo, I. Fault diagnosis based on extremely randomized trees in wireless sensor networks. Reliab Eng Syst Saf 2021;205:107284. https://doi.org/10.1016/j.ress.2020.107284.Search in Google Scholar
37. Wehenkel, L, Ernst, D, Geurts, P. Ensembles of extremely randomized trees and some generic applications. In: Proceedings of robust methods for power system state estimation and load forecasting; 2006:1–10 pp.Search in Google Scholar
38. Geurts, P, Ernst, D, Wehenkel, L. Extremely randomized trees. Mach Learn 2006;63:3–42. https://doi.org/10.1007/s10994-006-6226-1.Search in Google Scholar
39. Trojovský, P, Dehghani, M. Pelican optimization algorithm: a novel nature-inspired algorithm for engineering applications. Sensors 2022;22:855. https://doi.org/10.3390/s22030855.Search in Google Scholar PubMed PubMed Central
40. Al-Wesabi, FN, Mengash, HA, Marzouk, R, Alruwais, N, Allafi, R, Alabdan, R, et al.. Pelican optimization algorithm with federated learning driven attack detection model in internet of things environment. Future Gener Comput Syst 2023;148:118–27. https://doi.org/10.1016/j.future.2023.05.029.Search in Google Scholar
41. Rainio, O, Teuho, J, Klén, R. Evaluation metrics and statistical tests for machine learning. Sci Rep 2024;14:6086. https://doi.org/10.1038/s41598-024-56706-x.Search in Google Scholar PubMed PubMed Central
42. Wu, G, Zhu, J. Multi-label classification: do hamming loss and subset accuracy really conflict with each other? In: Advances in neural information processing systems 33 (NeurIPS 2020); 2020:3130–40 pp. Available from: https://arxiv.org/abs/2011.07805.Search in Google Scholar
43. Ao, SI. International MultiConference of engineers and computer scientists: IMECS 2013: 13-15 March, 2013. Kowloon, Hong Kong: Newswood Ltd.; 2013 The Royal Garden Hotel, International Association of Engineers.Search in Google Scholar
44. Chicco, D, Warrens, MJ, Jurman, G. The Matthews correlation coefficient (MCC) is more informative than Cohen’s Kappa and Brier score in binary classification assessment. IEEE Access 2021;9:78368–81. https://doi.org/10.1109/access.2021.3084050.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
