Ensemble Tree-Based Machine Learning for Predicting Volumetric Change in Lithium-Based Battery Electrode Materials

Arsenio Farrell Winoto; Gustina Alfa Trisnapradika

doi:10.30871/jaic.v10i4.13386

Authors

Arsenio Farrell Winoto Universitas Dian Nuswantoro
Gustina Alfa Trisnapradika Universitas Dian Nuswantoro

DOI:

https://doi.org/10.30871/jaic.v10i4.13386

Keywords:

Battery electrode materials, Ensemble tree models, Hyperparameter tuning, Machine learning, Volumetric change prediction

Abstract

Volumetric instability in lithium-based electrode materials remains a persistent challenge in electric vehicle battery development, as identifying stable material combinations through conventional laboratory methods is both time-consuming and resource-intensive. This study develops and compares three ensemble tree-based machine learning models, namely Random Forest, XGBoost, and CatBoost, to predict the maximum volume change percentage of lithium-based electrode materials. A dataset of 52,503 samples was constructed by integrating electrode pair data with structural and electronic features from the Materials Project API, enriched with compositional descriptors extracted using the Matminer Magpie preset. Each model underwent baseline evaluation followed by hyperparameter tuning using Optuna with Bayesian optimization over 100 trials, assessed using RMSE, MAE, and R². All three models achieved R² test above 0.98, with Random Forest yielding the best performance at RMSE of 17.1713, MAE of 4.0954, and R² test of 0.9900. SHAP analysis identified density discharge as the most determinant predictor across all models, reflecting its physicochemical role in representing the final crystal structure state following lithium intercalation. These findings confirm that ensemble tree-based models offer a reliable and efficient alternative to wet laboratory experimentation for lithium-based electrode material discovery.

Downloads

Download data is not yet available.

References

[1] M. F. Ng, Y. Sun, and Z. W. Seh, “Machine learning-inspired battery material innovation,” Energy Adv., vol. 2, no. 4, pp. 449–464, 2023, doi: 10.1039/d3ya00040k.

[2] E. Ndhlovu, D. Mhlanga, and B. Duri, “Correction: Decarbonising urban transport: an overview of electric vehicles, public transport, and sustainable infrastructure in achieving net-zero emissions (Discover Global Society, (2025), 3, 1, (53), 10.1007/s44282-025-00201-9),” Discov. Glob. Soc., vol. 3, no. 1, 2025, doi: 10.1007/s44282-025-00267-5.

[3] Z. Gao et al., “Electric vehicle lifecycle carbon emission reduction: A review,” Carbon Neutralization, vol. 2, no. 5, pp. 528–550, 2023, doi: 10.1002/cnl2.81.

[4] T. Rahman and 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, vol. 10, no. 7, 2024, doi: 10.3390/batteries10070220.

[5] L. Tang, P. Leung, Q. Xu, and C. Flox, “Machine Learning Orchestrating the Materials Discovery and Performance Optimization of Redox Flow Battery,” ChemElectroChem, vol. 11, no. 15, pp. 1–17, 2024, doi: 10.1002/celc.202400024.

[6] I. A. Moses, V. Barone, and J. E. Peralta, “Accelerating the discovery of battery electrode materials through data mining and deep learning models,” J. Power Sources, vol. 546, no. August, p. 231977, 2022, doi: 10.1016/j.jpowsour.2022.231977.

[7] N. Bhandari, G. J. Martis, and S. L. Gaonkar, “Advancements in lithium-ion batteries: sustainability and market impact,” Discov. Mater., vol. 5, no. 1, 2025, doi: 10.1007/s43939-025-00291-x.

[8] L. Grinsztajn, E. Oyallon, and G. Varoquaux, “Why do tree-based models still outperform deep learning on typical tabular data?,” Adv. Neural Inf. Process. Syst., vol. 35, no. NeurIPS, 2022.

[9] S. Uddin and H. Lu, “Confirming the statistically significant superiority of tree-based machine learning algorithms over their counterparts for tabular data,” PLoS One, vol. 19, no. 4 April, pp. 1–12, 2024, doi: 10.1371/journal.pone.0301541.

[10] G. Bree, H. Hao, Z. Stoeva, and C. T. John Low, “Monitoring state of charge and volume expansion in lithium-ion batteries: an approach using surface mounted thin-film graphene sensors,” RSC Adv., vol. 13, no. 10, pp. 7045–7054, 2023, doi: 10.1039/d2ra07572e.

[11] T. Kee and W. K. O. Ho, “Optimizing Machine Learning Models for Urban Sciences: A Comparative Analysis of Hyperparameter Tuning Methods,” Urban Sci., vol. 9, no. 9, 2025, doi: 10.3390/urbansci9090348.

[12] Y. Ma, P. Xu, M. Li, X. Ji, W. Zhao, and W. Lu, “The mastery of details in the workflow of materials machine learning,” npj Comput. Mater., vol. 10, no. 1, pp. 1–17, 2024, doi: 10.1038/s41524-024-01331-5.

[13] S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, no. 9, p. 100804, 2023, doi: 10.1016/j.patter.2023.100804.

[14] J. P. Lai, Y. L. Lin, H. C. Lin, C. Y. Shih, Y. P. Wang, and P. F. Pai, “Tree-Based Machine Learning Models with Optuna in Predicting Impedance Values for Circuit Analysis,” Micromachines, vol. 14, no. 2, 2023, doi: 10.3390/mi14020265.

[15] P. Heidari and A. Milan, “Combining K-fold cross validation with bayesian hyperparameter optimization for accuracy enhancement of land cover and land use classification,” Sci. Rep., vol. 15, no. 1, pp. 1–16, 2025, doi: 10.1038/s41598-025-23336-w.

[16] A. B. Hassanat et al., “A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric,” Mathematics, vol. 12, no. 22, pp. 1–20, 2024, doi: 10.3390/math12223623.

[17] J. M. H. Pinheiro et al., “The Impact of Feature Scaling in Machine Learning: Effects on Regression and Classification Tasks,” IEEE Access, vol. 13, no. November, pp. 199903–199931, 2025, doi: 10.1109/ACCESS.2025.3635541.

[18] C. Okolie et al., “Assessment of explainable tree-based ensemble algorithms for the enhancement of Copernicus digital elevation model in agricultural lands,” Int. J. Image Data Fusion, vol. 15, no. 4, pp. 430–460, 2024, doi: 10.1080/19479832.2024.2329563.

[19] F. Qayyum, M. A. Khan, D. H. Kim, H. Ko , and G. A. Ryu, “Explainable AI for Material Property Prediction Based on Energy Cloud: A Shapley-Driven Approach,” Materials (Basel)., vol. 16, no. 23, pp. 1–24, 2023, doi: 10.3390/ma16237322.

[20] H. Qin, Y. Zhang, Z. Guo, S. Wang, D. Zhao, and Y. Xue, “Prediction of Bandgap in Lithium-Ion Battery Materials Based on Explainable Boosting Machine Learning Techniques,” Materials (Basel)., vol. 17, no. 24, 2024, doi: 10.3390/ma17246217.