Element mapping-based Bayesian optimization framework enabling direct materials design: a case study on NASICON-type cathode materials
Source abstract
Abstract
Bayesian optimization (BO) helps in efficiently navigating complex and high-dimensional design spaces. Recently, it has been applied to materials science to discover novel materials with high performances. However, the application of BO to material design has been hindered by the challenges in handling discrete input variables, such as elements. This study introduces a novel element mapping strategy that encodes elemental identities into chemically meaningful continuous values, enabling the creation of easy-to-predict chemical spaces. This new framework is used to design high-capacity Na3V2(PO4)2F3 cathode materials for sodium-ion batteries, aiming to shift all working voltages into the desired operational voltage window (2.5–4.3 V). The proposed framework successfully suggested 16 optimal compositions within 50 iterations. The proposed approach can overcome the limitation of categorical input and broaden the applicability of BO to a wider range of material discoveries.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Advancements in Battery Materials · X-ray Diffraction in Crystallography
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. Agrawal, A. & Choudhary, A. Perspective: materials informatics and big data: realization of the “fourth paradigm” of science in materials science. APL Mater. 4, 053208 (2016).10.1063/1.4946894 ↗
2. Urban, A., Seo, D.-H. & Ceder, G. Computational understanding of Li-ion batteries. npj Comput. Mater. 2, 16002 (2016).10.1038/npjcompumats.2016.2 ↗
3. Greeley, J. et al. Computational high-throughput screening of electrocatalytic materials for hydrogen evolution. Nat. Mater. 5, 909–913 (2006).10.1038/nmat1752 ↗
4. Chen, C. et al. Graph networks as a universal machine learning framework for molecules and crystals. Chem. Mater. 31, 3564–3572 (2019).10.1021/acs.chemmater.9b01294 ↗
5. Shim, Y. et al. Data-driven design of NASICON-type electrodes using graph-based neural networks. Batter. Supercaps 7, e202400186 (2024).10.1002/batt.202400186 ↗
6. Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120, 145301 (2018).10.1103/PhysRevLett.120.145301 ↗
7. Chen, C. & Ong, S. P. A universal graph deep learning interatomic potential for the periodic table. Nat. Comput. Sci. 2, 718–728 (2022).10.1038/s43588-022-00349-3 ↗
8. Brochu, E., Cora, V. M., & Freitas, N.d. A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv:1012.2599, 2010.
9. Frazier, P. I., A tutorial on Bayesian optimization. arXiv:1807.02811, 2018.10.1287/educ.2018.0188 ↗
10. Snoek, J., Larochelle, H., & Adams, R. P. Practical Bayesian optimization of machine learning algorithms. arXiv:1206.2944, 2012.
11. Rasmussen, C. E. & Williams, C. Gaussian Processes for Machine Learning (MIT Press, 2006).10.7551/mitpress/3206.001.0001 ↗
12. Pedersen, J. K. et al. Bayesian optimization of high-entropy alloy compositions for electrocatalytic oxygen reduction. Angew. Chem. Int. Ed. Engl. 60, 24144–24152 (2021).10.1002/anie.202108116 ↗
13. Duquesnoy, M. et al. Machine learning-assisted multi-objective optimization of battery manufacturing from synthetic data generated by physics-based simulations. Energy Stor. Mater. 56, 50–61 (2023).
14. Mohammadi, H., P. Challenor, M. Goodfellow, and D. Williamson, Emulating computer models with step-discontinuous outputs using Gaussian processes. arXiv:1903.02071v4, 2020.
15. Luong, P. et al. Bayesian optimization with discrete variables, in AI 2019. Advances in Artificial Intelligence. (2019) p. 473–484.10.1007/978-3-030-35288-2_38 ↗
16. Hwang, J. Y., Myung, S. T. & Sun, Y. K. Sodium-ion batteries: present and future. Chem. Soc. Rev. 46, 3529–3614 (2017).10.1039/C6CS00776G ↗
17. Zhao, L. et al. Engineering of sodium-ion batteries: opportunities and challenges. Engineering 24, 172–183 (2023).10.1016/j.eng.2021.08.032 ↗
18. Xiang, X., Zhang, K. & Chen, J. Recent advances and prospects of cathode materials for sodium-ion batteries. Adv. Mater. 27, 5343–5364 (2015).10.1002/adma.201501527 ↗
19. Xu, C. et al. A novel NASICON-typed Na4VMn0.5Fe0.5(PO4)3 cathode for high-performance Na-ion batteries. Adv. Energy. Mater. 11, 2100729 (2021).10.1002/aenm.202100729 ↗
20. Zhu, C. et al. A high power–high energy Na3V2(PO4)2F3 sodium cathode: investigation of transport parameters, rational design and realization. Chem. Mater. 29, 5207–5215 (2017).10.1021/acs.chemmater.7b00927 ↗
21. Anantharamulu, N. et al. A wide-ranging review on Nasicon type materials. J. Mater. Sci. 46, 2821–2837 (2011).10.1007/s10853-011-5302-5 ↗
22. Wang, M. et al. Synthesis and electrochemical performances of Na3V2(PO4)2F3/C composites as cathode materials for sodium ion batteries. RSC Adv. 9, 30628–30636 (2019).10.1039/C9RA05089B ↗
23. Yan, G. et al. Higher energy and safer sodium ion batteries via an electrochemically made disordered Na3V2(PO4)2F3 material. Nat. Commun. 10, 585 (2019).10.1038/s41467-019-08359-y ↗
24. Mani Kanta, P. L. et al. Outstanding specific energy achieved via reversible cycling of V4+/V2+ redox couple in N-doped carbon coated Na3V2(PO4)2F3: An ex-situ XRD, XPS and XAS study. Mater. Today Energy 48, 101802 (2025).10.1016/j.mtener.2025.101802 ↗
25. Gramacy, R. B. Surrogates-Gaussian Process Modeling, Design, and Optimization for the Applied Sciences (CRC Press, 2020).10.1201/9780367815493 ↗
26. Bai, Q. et al. Computational studies of electrode materials in sodium-ion batteries. Adv. Energy. Mater. 8, 1702998 (2018).10.1002/aenm.201702998 ↗
27. Zhao, D. et al. Machine-learning-assisted modeling of alloy ordering phenomena at the electronic scale through electronegativity. Appl. Phys. Lett. 124, 111902 (2024).10.1063/5.0188516 ↗
28. Li, Z., Ma, X. & Xin, H. Feature engineering of machine-learning chemisorption models for catalyst design. Catal. Today 280, 232–238 (2017).10.1016/j.cattod.2016.04.013 ↗
29. Noh, J. et al. Active learning with non-ab initio input features toward efficient CO2 reduction catalysts. Chem. Sci. 9, 5152–5159 (2018).10.1039/C7SC03422A ↗
30. Tang, W., Sanville, E. & Henkelman, G. A grid-based Bader analysis algorithm without lattice bias. J. Phys. Condens. Matter. 21, 084204 (2009).10.1088/0953-8984/21/8/084204 ↗
31. Kresse, G. & Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B 54, 169–186 (1996).10.1103/PhysRevB.54.11169 ↗
32. Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865–3868 (1996).10.1103/PhysRevLett.77.3865 ↗
33. Monkhorst, H. J. & Pack, J. D. Special points for Brillouin-zone integrations. Phys. Rev. B 13, 5188–5192 (1976).10.1103/PhysRevB.13.5188 ↗
34. Dudarev, S. L. et al. Electron-energy-loss spectra and the structural stability of nickel oxide: an LSDA+U study. Phys. Rev. B 57, 1505–1509 (1998).10.1103/PhysRevB.57.1505 ↗
35. Wang, L., Maxisch, T. & Ceder, G. Oxidation energies of transition metal oxides within the GGA+U framework. Phys. Rev. B. 73, 195107 (2006).10.1103/PhysRevB.73.195107 ↗
36. Harun, K. et al. DFT + U calculations for electronic, structural, and optical properties of ZnO wurtzite structure: a review. Results Phys. 16, 102829 (2020).10.1016/j.rinp.2019.102829 ↗
37. Momma, K. & Izumi, F. VESTA: a three-dimensional visualization system for electronic and structural analysis. J. Appl. Crystallogr. 41, 653–658 (2008).10.1107/S0021889808012016 ↗
38. Agrawal, R. Sample mean based index policies with O(log n) regret for the multi-armed bandit problem. Adv. Appl. Probab. 27, 1054–1078 (1995).10.2307/1427934 ↗
39. Nogueira, F. Bayesian Optimization: Open source constrained global optimization tool for Python. GitHub repository, 2014. Available at: https://github.com/bayesian-optimization/BayesianOptimization.