Chemical foundation model-guided design of high ionic conductivity electrolyte formulations
Source abstract
Abstract
Designing optimal formulations is a major challenge in developing electrolytes for the next generation of rechargeable batteries due to the vast combinatorial design space and complex interplay between multiple constituents. Machine learning (ML) offers a powerful tool to uncover underlying chemical design rules and accelerate the process of formulation discovery. In this work, we present an approach to design new formulations that can achieve target performance, using a generalizable chemical foundation model. The chemical foundation model is fine-tuned on an experimental dataset of 13,666 ionic conductivity values curated from the lithium-ion battery literature. The fine-tuned model is used to discover 7 novel high conductivity electrolyte formulations through generative screening, improving the conductivity of LiFSI- and LiDFOB-based electrolytes by 82% and 172%, respectively. These findings highlight a generalizable workflow that is highly adaptable to the discovery of chemical mixtures with tailored properties to address challenges in energy storage and beyond.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Materials and Technologies · Fuel Cells and Related Materials · Ionic liquids properties and applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (78)
Show source-provided references
1. Bannigan, P. et al. Machine learning directed drug formulation development. Adv. Drug Deliv. Rev. 175, 113806 (2021).10.1016/j.addr.2021.05.016 ↗
2. Sandoval-Pauker, C. et al. Computational chemistry as applied in environmental research: opportunities and challenges. ACS EST Eng. 4, 66–95 (2024).10.1021/acsestengg.3c00227 ↗
3. Gomes, G., dos, P., Pollice, R. & Aspuru-Guzik, A. Navigating through the maze of homogeneous catalyst design with machine learning. Trends Chem. 3, 96–110 (2021).10.1016/j.trechm.2020.12.006 ↗
4. Xin, H., Virk, A. S., Virk, S. S., Akin-Ige, F. & Amin, S. Applications of artificial intelligence and machine learning on critical materials used in cosmetics and personal care formulation design. Curr. Opin. Colloid Interface Sci. 73, 101847 (2024).10.1016/j.cocis.2024.101847 ↗
5. Meng, Y. S., Srinivasan, V. & Xu, K. Designing better electrolytes. Science 378, eabq3750 (2022).10.1126/science.abq3750 ↗
6. Narayanan, H. et al. Machine learning for biologics: opportunities for protein engineering, developability, and formulation. Trends Pharmacol. Sci. 42, 151–165 (2021).10.1016/j.tips.2020.12.004 ↗
7. Benayad, A. et al. High-throughput experimentation and computational freeway lanes for accelerated battery electrolyte and interface development research. Adv. Energy Mater. 12, 2102678 (2022).10.1002/aenm.202102678 ↗
8. Ling, C. A review of the recent progress in battery informatics. NPJ Comput. Mater. 8, 1–22 (2022).10.1038/s41524-022-00713-x ↗
9. Zhang, S. S., Jow, T. R., Amine, K. & Henriksen, G. L. LiPF6–EC–EMC electrolyte for Li-ion battery. J. Power Sources 107, 18–23 (2002).10.1016/S0378-7753(01)00968-5 ↗
10. Aravindan, V., Gnanaraj, J., Madhavi, S. & Liu, H.-K. Lithium-ion conducting electrolyte salts for lithium batteries. Chem. Eur. J. 17, 14326–14346 (2011).10.1002/chem.201101486 ↗
11. Aurbach, D. et al. Design of electrolyte solutions for Li and Li-ion batteries: a review. Electrochim. Acta 50, 247–254 (2004).10.1016/j.electacta.2004.01.090 ↗
12. Logan, E. R. & Dahn, J. R. Electrolyte design for fast-charging Li-ion batteries. Trends Chem. 2, 354–366 (2020).10.1016/j.trechm.2020.01.011 ↗
13. Bian, X. et al. A novel lithium difluoro(oxalate) borate and lithium hexafluoride phosphate dual-salt electrolyte for Li-excess layered cathode material. J. Alloy. Compd. 736, 136–142 (2018).10.1016/j.jallcom.2017.11.126 ↗
14. Colclasure, A. M. et al. Requirements for enabling extreme fast charging of high energy density Li-ion cells while avoiding lithium plating. J. Electrochem. Soc. 166, A1412 (2019).10.1149/2.0451908jes ↗
15. Gallagher, K. G. et al. Optimizing areal capacities through understanding the limitations of lithium-ion electrodes. J. Electrochem. Soc. 163, A138 (2015).10.1149/2.0321602jes ↗
16. Weiss, M. et al. Fast charging of lithium-ion batteries: a review of materials aspects. Adv. Energy Mater. 11, 2101126 (2021).10.1002/aenm.202101126 ↗
17. Xu, K. Electrolytes and interphases in Li-ion batteries and beyond. Chem. Rev. 114, 11503–11618 (2014).10.1021/cr500003w ↗
18. Seo, D. M. et al. Role of mixed solvation and ion pairing in the solution structure of lithium ion battery electrolytes.–J. Phys. Chem. C 119, 14038–14046 (2015).10.1021/acs.jpcc.5b03694 ↗
19. Hubble, D. et al. Liquid electrolyte development for low-temperature lithium-ion batteries. Energy Environ. Sci. 15, 550–578 (2022).10.1039/D1EE01789F ↗
20. Zhang, H., Wang, Z., Cai, J., Wu, S. & Li, J. Machine-learning-enabled tricks of the trade for rapid host material discovery in Li–S battery. ACS Appl. Mater. Interfaces 13, 53388–53397 (2021).10.1021/acsami.1c10749 ↗
21. Li, S. & Barnard, A. S. Inverse design of MXenes for high-capacity energy storage materials using multi-target machine learning. Chem. Mater. 34, 4964–4974 (2022).10.1021/acs.chemmater.2c00200 ↗
22. Merchant, A. et al. Scaling deep learning for materials discovery. Nature 624, 80–85 (2023).10.1038/s41586-023-06735-9 ↗
23. Rittig, J. G., Ben Hicham, K., Schweidtmann, A. M., Dahmen, M. & Mitsos, A. Graph neural networks for temperature-dependent activity coefficient prediction of solutes in ionic liquids. Comput. Chem. Eng. 171, 108153 (2023).10.1016/j.compchemeng.2023.108153 ↗
24. Kumar, R., Vu, M. C., Ma, P. & Amanchukwu, C. Electrolytomics: a unified big data approach for electrolyte design and discovery. Chem. Mater 37, 2720–2734 (2024).10.1021/acs.chemmater.4c03196 ↗
25. Zhang, H. et al. Learning molecular mixture property using chemistry-aware graph neural network. PRX Energy 3, 023006 (2024).10.1103/PRXEnergy.3.023006 ↗
26. Zhu, S. et al. Differentiable modeling and optimization of non-aqueous Li-based battery electrolyte solutions using geometric deep learning. Nat. Commun. 15, 8649 (2024).10.1038/s41467-024-51653-7 ↗
27. Sharma, V. et al. Formulation graphs for mapping structure-composition of battery electrolytes to device performance. J. Chem. Inf. Model. 63, 6998–7010 (2023).10.1021/acs.jcim.3c01030 ↗
28. Sharma, V., Tek, A., Nguyen, K., Giammona, M., Zohair, M., Sundberg, L. & La, Y. H. Improving electrolyte performance for target cathode loading using an interpretable data-driven approach. Cell Reports Physical Science 6, 102347 (2025).10.1016/j.xcrp.2024.102347 ↗
29. Dave, A. et al. Autonomous discovery of battery electrolytes with robotic experimentation and machine learning. Cell Rep. Phys. Sci. 1, 100264 (2020).10.1016/j.xcrp.2020.100264 ↗
30. Flores, E. et al. Learning the laws of lithium-ion transport in electrolytes using symbolic regression. Digit. Discov. 1, 440–447 (2022).10.1039/D2DD00027J ↗
31. Yan, P. et al. Non-aqueous battery electrolytes: high-throughput experimentation and machine learning-aided optimization of ionic conductivity. J. Mater. Chem. A 12, 19123–19136 (2024).10.1039/D3TA06249J ↗
32. Baskin, I., Epshtein, A. & Ein-Eli, Y. Benchmarking machine learning methods for modeling physical properties of ionic liquids. J. Mol. Liq. 351, 118616 (2022).10.1016/j.molliq.2022.118616 ↗
33. Bilodeau, C. et al. Machine learning for predicting the viscosity of binary liquid mixtures. Chem. Eng. J. 464, 142454 (2023).10.1016/j.cej.2023.142454 ↗
34. Kim, S. C. et al. Data-driven electrolyte design for lithium metal anodes. Proc. Natl. Acad. Sci. USA 120, e2214357120 (2023).10.1073/pnas.2214357120 ↗
35. Wigh, D. S., Goodman, J. M. & Lapkin, A. A. A review of molecular representation in the age of machine learning. WIREs Comput. Mol. Sci. 12, e1603 (2022).10.1002/wcms.1603 ↗
36. Haghighatlari, M. et al. Learning to make chemical predictions: the interplay of feature representation, data, and machine learning methods. Chem 6, 1527–1542 (2020).10.1016/j.chempr.2020.05.014 ↗
37. Wang, S., Guo, Y., Wang, Y., Sun, H. & Huang, J. SMILES-BERT: large scale unsupervised pre-training for molecular property prediction. In Proc. 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 429–436 (ACM, 2019).10.1145/3307339.3342186 ↗
38. Ross, J. et al. Large-scale chemical language representations capture molecular structure and properties. Nat. Mach. Intell. 4, 1256–1264 (2022).10.1038/s42256-022-00580-7 ↗
39. Yüksel, A., Ulusoy, E., Ünlü, A. & Doğan, T. SELFormer: molecular representation learning via SELFIES language models. Mach. Learn. Sci. Technol. 4, 025035 (2023).10.1088/2632-2153/acdb30 ↗
40. Pyzer-Knapp, E. O. et al. Foundation models for materials discovery—current state and future directions. NPJ Comput. Mater. 11, 1–10 (2025).10.1038/s41524-025-01538-0 ↗
41. Flam-Shepherd, D., Zhu, K. & Aspuru-Guzik, A. Language models can learn complex molecular distributions. Nat. Commun. 13, 3293 (2022).10.1038/s41467-022-30839-x ↗
42. Soares, E., Sharma, V., Brazil, E.V., Cerqueira, R. & Na, Y.H. Capturing formulation design of battery electrolytes with chemical large language model. AI for Accelerated Materials Design-NeurIPS 2023 Workshop. Preprint at https://doi.org/10.21203/rs.3.rs-3593035/v1 (2024).10.21203/rs.3.rs-3593035/v1 ↗
43. Priyadarsini, I., Sharma, V., Takeda, S., Kishimoto, A., Hamada, L. & Shinohara, H. Improving Performance Prediction of Electrolyte Formulations with Transformer-based Molecular Representation Model. ICML'24 Workshop ML for Life and Material Science: From Theory to Industry Applications. Preprint at https://doi.org/10.48550/arXiv.2406.19792 (2024).10.48550/arXiv.2406.19792 ↗
44. Soares, E., Vital Brazil, E., Shirasuna, V., Zubarev, D., Cerqueira, R., & Schmidt, K. An open-source family of large encoder-decoder foundation models for chemistry. Communications Chemistry, 8, 193 (2025).10.1038/s42004-025-01585-0 ↗
45. Narayanan Krishnamoorthy, A. et al. Data-driven analysis of high-throughput experiments on liquid battery electrolyte formulations: unraveling the impact of composition on conductivity. Chem. Methods 2, e202200008 (2022).10.1002/cmtd.202200008 ↗
46. Hall, D. S. et al. Exploring classes of co-solvents for fast-charging lithium-ion cells. J. Electrochem. Soc. 165, A2365 (2018).10.1149/2.1351810jes ↗
47. Hossain, M. J. et al. The relationship between ionic conductivity and solvation structures of localized high-concentration fluorinated electrolytes for lithium-ion batteries. J. Phys. Chem. Lett. 14, 7718–7731 (2023).10.1021/acs.jpclett.3c01453 ↗
48. Watanabe, Y., Ugata, Y., Ueno, K., Watanabe, M. & Dokko, K. Does Li-ion transport occur rapidly in localized high-concentration electrolytes? Phys. Chem. Chem. Phys. 25, 3092–3099 (2023).10.1039/D2CP05319E ↗
49. Bergstrom, H. K. & McCloskey, B. D. Ion transport in (localized) high concentration electrolytes for Li-based batteries. ACS Energy Lett. 9, 373–380 (2024).10.1021/acsenergylett.3c01662 ↗
50. Wang, Q. et al. High entropy liquid electrolytes for lithium batteries. Nat. Commun. 14, 440 (2023).10.1038/s41467-023-36075-1 ↗
51. de Blasio, P., Elsborg, J., Vegge, T., Flores, E. & Bhowmik, A. CALiSol-23: experimental electrolyte conductivity data for various Li-salts and solvent combinations. Sci. Data 11, 750 (2024).10.1038/s41597-024-03575-8 ↗
52. Mauger, A., Julien, C. M., Paolella, A., Armand, M. & Zaghib, K. A comprehensive review of lithium salts and beyond for rechargeable batteries: progress and perspectives. Mater. Sci. Eng. R. Rep. 134, 1–21 (2018).10.1016/j.mser.2018.07.001 ↗
53. Becht, E. et al. Dimensionality reduction for visualizing single-cell data using UMAP. Nat. Biotechnol. 37, 38–44 (2019).10.1038/nbt.4314 ↗
54. Durant, J. L., Leland, B. A., Henry, D. R. & Nourse, J. G. Reoptimization of MDL keys for use in drug discovery. J. Chem. Inf. Comput. Sci. 42, 1273–1280 (2002).10.1021/ci010132r ↗
55. Qu, J. et al. Leveraging language representation for materials exploration and discovery. NPJ Comput. Mater. 10, 1–14 (2024).10.1038/s41524-024-01231-8 ↗
56. Soares, E. et al. A Mamba-based foundation model for materials. NPJ Artif. Intell. 1, 8 (2025).10.1038/s44387-025-00009-7 ↗
57. Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1, 4171–4186, Association for Computational Linguistics (2019).
58. Takashige, S., Hanai, M., Suzumura, T., Wang, L. & Taura, K. Is self-supervised pretraining good for extrapolation in molecular property prediction? Preprint at https://doi.org/10.48550/arXiv.2308.08129 (2023).10.48550/arXiv.2308.08129 ↗
59. Li, K., Wang, J., Song, Y. & Wang, Y. Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries. Nat. Commun. 14, 2789 (2023).10.1038/s41467-023-38493-7 ↗
60. Xiao, L. F., Cao, Y. L., Ai, X. P. & Yang, H. X. Optimization of EC-based multi-solvent electrolytes for low temperature applications of lithium-ion batteries. Electrochim. Acta 49, 4857–4863 (2004).10.1016/j.electacta.2004.05.038 ↗
61. Zhou, H., Fang, Z. & Li, J. LiPF6 and lithium difluoro(oxalato)borate/ethylene carbonate + dimethyl carbonate + ethyl(methyl)carbonate electrolyte for Li4Ti5O12 anode. J. Power Sources 230, 148–154 (2013).10.1016/j.jpowsour.2012.11.060 ↗
62. Xie, J. & Lu, Y.-C. Designing nonflammable liquid electrolytes for safe Li-ion batteries. Adv. Mater. 37, 2312451 (2025).10.1002/adma.202312451 ↗
63. Seo, D. M. et al. Electrolyte solvation and ionic association. J. Electrochem. Soc. 159, A553 (2012).10.1149/2.jes112264 ↗
64. Kim, S. C. et al. High-entropy electrolytes for practical lithium metal batteries. Nat. Energy 8, 814–826 (2023).10.1038/s41560-023-01280-1 ↗
65. Brandon, E. J., Smart, M. C. & West, W. C. Low-temperature performance of electrochemical capacitors using acetonitrile/methyl formate electrolytes and activated carbon fabric electrodes. J. Mater. Res. 35, 113–121 (2020).10.1557/jmr.2019.396 ↗
66. Ein-Eli, Y., Thomas, S. R. & Koch, V. R. New electrolyte system for Li-ion battery. J. Electrochem. Soc. 143, L195 (1996).10.1149/1.1837084 ↗
67. Qian, X., Yoon, B.-J., Arróyave, R., Qian, X. & Dougherty, E. R. Knowledge-driven learning, optimization, and experimental design under uncertainty for materials discovery. Patterns 4, 100863 (2023).10.1016/j.patter.2023.100863 ↗
68. Lookman, T., Balachandran, P. V., Xue, D. & Yuan, R. Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design. NPJ Comput. Mater. 5, 1–17 (2019).10.1038/s41524-019-0153-8 ↗
69. Schedlbauer, T. et al. Lithium difluoro(oxalato)borate: a promising salt for lithium metal based secondary batteries? Electrochim. Acta 92, 102–107 (2013).10.1016/j.electacta.2013.01.023 ↗
70. Lazar, M. L. & Lucht, B. L. Carbonate free electrolyte for lithium ion batteries containing γ-butyrolactone and methyl butyrate. J. Electrochem. Soc. 162, A928 (2015).10.1149/2.0601506jes ↗
71. Gu, Y., Fang, S., Yang, L. & Hirano, S. A safe electrolyte for high-performance lithium-ion batteries containing lithium difluoro(oxalato)borate, gamma-butyrolactone and non-flammable hydrofluoroether. Electrochim. Acta 394, 139120 (2021).10.1016/j.electacta.2021.139120 ↗
72. Milad, A. et al. Development of ensemble machine learning approaches for designing fiber-reinforced polymer composite strain prediction model. Eng. Comput. 38, 3625–3637 (2022).10.1007/s00366-021-01398-4 ↗
73. Ni, L., Xu, G., Li, C. & Cui, G. Electrolyte formulation strategies for potassium-based batteries. Exploration 2, 20210239 (2022).10.1002/EXP.20210239 ↗
74. Yang, Y., Yang, W., Yang, H. & Zhou, H. Electrolyte design principles for low-temperature lithium-ion batteries. eScience 3, 100170 (2023).10.1016/j.esci.2023.100170 ↗
75. Bradford, G. et al. Chemistry-informed machine learning for polymer electrolyte discovery. ACS Cent. Sci. 9, 206–216 (2023).10.1021/acscentsci.2c01123 ↗
76. Kim, S., Noh, J., Gu, G. H., Aspuru-Guzik, A. & Jung, Y. Generative adversarial networks for crystal structure prediction. ACS Cent. Sci. 6, 1412–1420 (2020).10.1021/acscentsci.0c00426 ↗
77. Njirjak, M. et al. Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning. Nat. Mach. Intell. 6, 1487–1500 (2024).10.1038/s42256-024-00928-1 ↗
78. Singh, A. K. & Strouse, D. J. Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs. Preprint at https://doi.org/10.48550/arXiv.2402.14903 (2024).10.48550/arXiv.2402.14903 ↗