A database of experimentally measured lithium solid electrolyte conductivities evaluated with machine learning
Source abstract
Abstract
Abstract The application of machine learning models to predict material properties is determined by the availability of high-quality data. We present an expert-curated dataset of lithium ion conductors and associated lithium ion conductivities measured by a.c. impedance spectroscopy. This dataset has 820 entries collected from 214 sources; entries contain a chemical composition, an expert-assigned structural label, and ionic conductivity at a specific temperature (from 5 to 873 °C). There are 403 unique chemical compositions with an associated ionic conductivity near room temperature (15–35 °C). The materials contained in this dataset are placed in the context of compounds reported in the Inorganic Crystal Structure Database with unsupervised machine learning and the Element Movers Distance. This dataset is used to train a CrabNet-based classifier to estimate whether a chemical composition has high or low ionic conductivity. This classifier is a practical tool to aid experimentalists in prioritizing candidates for further investigation as lithium ion conductors.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Materials and Technologies · Machine Learning in Materials Science · Advancements in Battery Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (56)
Show source-provided references
1. Goodenough, J. B. Rechargeable batteries: challenges old and new. J. Solid State Electrochem. 16, 2019–2029 (2012).10.1007/s10008-012-1751-2 ↗
2. Knauth, P. Inorganic solid Li ion conductors: an overview. Solid State Ion. 180, 911–916 (2009).10.1016/j.ssi.2009.03.022 ↗
3. Janek, J. & Zeier, W. G. A solid future for battery development. Nat. Energy 1, 1–4 (2016).10.1038/nenergy.2016.141 ↗
4. Wang, Y. et al. Design principles for solid-state lithium superionic conductors. Nat. Mater. 14, 1026–1031 (2015).10.1038/nmat4369 ↗
5. Bachman, J. C. et al. Inorganic solid-state electrolytes for lithium batteries: mechanisms and properties governing ion conduction. Chem. Rev. 116, 140–162 (2016).10.1021/acs.chemrev.5b00563 ↗
6. Lombardo, T. et al. Artificial intelligence applied to battery research: hype or reality? Chem. Rev. https://doi.org/10.1021/acs.chemrev.1c00108 (2021).10.1021/acs.chemrev.1c00108 ↗
7. Sendek, A. D., Cheon, G., Pasta, M. & Reed, E. J. Quantifying the search for solid Li-ion electrolyte materials by anion: a data-driven perspective. J. Phys. Chem. 124, 8067–8079 (2020).
8. Zhang, Y. et al. Unsupervised discovery of solid-state lithium ion conductors. Nat. Commun. 10, 5260 (2019).10.1038/s41467-019-13214-1 ↗
9. Cubuk, E. D., Sendek, A. D. & Reed, E. J. Screening billions of candidates for solid lithium-ion conductors: a transfer learning approach for small data. J. Chem. Phys. 150, 214701 (2019).10.1063/1.5093220 ↗
10. Haghighatlari, M., Shih, C.-Y. & Hachmann, J. Thinking globally, acting locally: on the issue of training set imbalance and the case for local machine learning models in chemistry. Preprint at https://chemrxiv.org/engage/chemrxiv/article-details/60c745c4337d6cef32e2704f (2019).10.26434/chemrxiv.8796947.v2 ↗
11. De Breuck, P.-P., Evans, M. L. & Rignanese, G.-M. Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet. J. Phys. Condens. Matter 33, 404002 (2021).10.1088/1361-648X/ac1280 ↗
12. Dunn, A., Wang, Q., Ganose, A., Dopp, D. & Jain, A. Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm. Npj Comput. Mater. 6, 1–10 (2020).10.1038/s41524-019-0267-z ↗
13. Irvine, J. T. S., Sinclair, D. C. & West, A. R. Electroceramics: characterization by impedance spectroscopy. Adv. Mater. 2, 132–138 (1990).10.1002/adma.19900020304 ↗
14. Tshitoyan, V. et al. Unsupervised word embeddings capture latent knowledge from materials science literature. Nature 571, 95–98 (2019).10.1038/s41586-019-1335-8 ↗
15. Court, C. J. & Cole, J. M. Auto-generated materials database of Curie and Néel temperatures via semi-supervised relationship extraction. Sci. Data 5, 180111 (2018).10.1038/sdata.2018.111 ↗
16. Sendek, A. D. et al. Holistic computational structure screening of more than 12,000 candidates for solid lithium-ion conductor materials. Energy Environ. Sci. 10, 306–320 (2017).10.1039/C6EE02697D ↗
17. Fergus, J. W. Ceramic and polymeric solid electrolytes for lithium-ion batteries. J. Power Sources 195, 4554–4569 (2010).10.1016/j.jpowsour.2010.01.076 ↗
18. Rossbach, A., Tietz, F. & Grieshammer, S. Structural and transport properties of lithium-conducting NASICON materials. J. Power Sources 391, 1–9 (2018).10.1016/j.jpowsour.2018.04.059 ↗
19. Stramare, S., Thangadurai, V. & Weppner, W. Lithium lanthanum titanates: a review. Chem. Mater. 15, 3974–3990 (2003).10.1021/cm0300516 ↗
20. Zhang, Z. et al. New horizons for inorganic solid state ion conductors. Energy Environ. Sci. 11, 1945–1976 (2018).10.1039/C8EE01053F ↗
21. Chen, C. & Du, J. Lithium ion diffusion mechanism in lithium lanthanum titanate solid-state electrolytes from atomistic. Simul. J. Am. Ceram. Soc. 98, 534–542 (2015).10.1111/jace.13307 ↗
22. Xiang, Y.-X. et al. Toward understanding of ion dynamics in highly conductive lithium ion conductors: some perspectives by solid state NMR techniques. Solid State Ion. 318, 19–26 (2018).10.1016/j.ssi.2017.11.025 ↗
23. Nolan, A. M., Zhu, Y., He, X., Bai, Q. & Mo, Y. Computation-accelerated design of materials and interfaces for all-solid-state lithium-ion batteries. Joule 2, 2016–2046 (2018).10.1016/j.joule.2018.08.017 ↗
24. Manawan, M., Kartini, E. & Avdeev, M. Visualizing lithium ions in the crystal structure of Li3PO4 by in situ neutron diffraction. J. Appl. Crystallogr. 54, 1409–1415 (2021).10.1107/S1600576721008700 ↗
25. Radford, A. et al. Language Models are Unsupervised Multitask Learners. OpenAI Blog https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf (2019).
26. Wolf, T. et al. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations 38–45 (Association for Computational Linguistics, 2020).
27. Ling, C. A review of the recent progress in battery informatics. Npj Comput. Mater. 8, 33 (2022).10.1038/s41524-022-00713-x ↗
28. Hargreaves, C. J., Dyer, M. S., Gaultois, M. W., Kurlin, V. A. & Rosseinsky, M. J. The Earth mover’s distance as a metric for the space of inorganic compositions. Chem. Mater. 32, 10610–10620 (2020).10.1021/acs.chemmater.0c03381 ↗
29. Levin, I. NIST Inorganic Crystal Structure Database (ICSD) https://doi.org/10.18434/M32147 (2020).10.18434/M32147 ↗
30. Krzanowski, W. Principles of Multivariate Analysis Ch. 2 (Oxford University Press, 2000).10.1093/oso/9780198507086.001.0001 ↗
31. Kobak, D. & Linderman, G. C. Initialization is critical for preserving global data structure in both t-SNE and UMAP. Nat. Biotechnol. 39, 156–157 (2021).10.1038/s41587-020-00809-z ↗
32. McInnes, L., Healy, J., Saul, N. & Großberger, L. UMAP: Uniform Manifold Approximation and Projection. J. Open Source Softw. 3, 861 (2018).10.21105/joss.00861 ↗
33. Ester, M., Kriegel, H.-P., Sander, J. & Xu, X. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining 226–231 (1996).
34. Murdock, R. J., Kauwe, S. K., Wang, A. Y. T. & Sparks, T. D. Is domain knowledge necessary for machine learning materials properties? Integrating Mater. Manuf. Innov. 9, 221–227 (2020).10.1007/s40192-020-00179-z ↗
35. Wang, A. Y.-T. et al. Machine learning for materials scientists: an introductory guide toward best practices. Chem. Mater. 32, 4954–4965 (2020).10.1021/acs.chemmater.0c01907 ↗
36. Ho, T. K. Random decision forests. In Proceedings of 3rd International Conference on Document Analysis and Recognition Vol. 1, 278–282 (1995).10.1109/ICDAR.1995.598994 ↗
37. He, X., Zhao, K. & Chu, X. AutoML: A survey of the state-of-the-art. Knowl. -Based Syst. 212, 106622 (2021).10.1016/j.knosys.2020.106622 ↗
38. Feurer, M. et al. Efficient and robust automated machine learning. In Proceedings of the 28th International Conference on Neural Information Processing Systems Vol. 2, 2755–2763 (2015).
39. Wang, A. Y.-T., Kauwe, S. K., Murdock, R. J. & Sparks, T. D. Compositionally restricted attention-based network for materials property predictions. Npj Comput. Mater. 7, 1–10 (2021).10.1038/s41524-021-00545-1 ↗
40. Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 6000–6010 (2017).
41. Goodall, R. E. A. & Lee, A. A. Predicting materials properties without crystal structure: deep representation learning from stoichiometry. Nat. Commun. 11, 6280 (2020).10.1038/s41467-020-19964-7 ↗
42. Kong, S., Guevarra, D., Gomes, C. P. & Gregoire, J. M. Materials representation and transfer learning for multi-property prediction. Appl. Phys. Rev. 8, 021409 (2021).10.1063/5.0047066 ↗
43. Kirklin, S. et al. The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies. Npj Comput. Mater. 1, 1–15 (2015).10.1038/npjcompumats.2015.10 ↗
44. Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016).
45. Matthews, B. W. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim. Biophys. Acta BBA - Protein Struct. 405, 442–451 (1975).10.1016/0005-2795(75)90109-9 ↗
46. Chicco, D. & Jurman, G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21, 6 (2020).10.1186/s12864-019-6413-7 ↗
47. Stanev, V. et al. Machine learning modeling of superconducting critical temperature. Npj Comput. Mater. 4, 1–14 (2018).10.1038/s41524-018-0085-8 ↗
48. Suzuki, K. et al. Synthesis, structure, and electrochemical properties of crystalline Li–P–S–O solid electrolytes: novel lithium-conducting oxysulfides of Li10GeP2S12 family. Solid State Ion. 288, 229–234 (2016).10.1016/j.ssi.2016.02.002 ↗
49. Gamon, J. et al. Li4.3AlS3.3Cl0.7: a sulfide–chloride lithium ion conductor with highly disordered structure and increased conductivity. Chem. Mater. 33, 8733–8744 (2021).10.1021/acs.chemmater.1c02751 ↗
50. Jiang, Y., Hu, Z., Ling, M. & Zhu, X. A comparative study of Li10.35Ge1.35P1.65S12 and Li10.5Ge1.5P1.5S12 superionic conductors. Funct. Mater. Lett. 13, 2050031 (2020).10.1142/S1793604720500319 ↗
51. Sun, Y., Suzuki, K., Hori, S., Hirayama, M. & Kanno, R. Superionic conductors: Li10+δ[SnySi1–y]1+δP2−δS12 with a Li10GeP2S12-type structure in the Li3PS4–Li4SnS4–Li4SiS4 quasi-ternary system. Chem. Mater. 29, 5858–5864 (2017).10.1021/acs.chemmater.7b00886 ↗
52. Sun, Y. et al. Oxygen substitution effects in Li10GeP2S12 solid electrolyte. J. Power Sources 324, 798–803 (2016).10.1016/j.jpowsour.2016.05.100 ↗
53. Hori, S., Suzuki, K., Hirayama, M., Kato, Y. & Kanno, R. Lithium superionic conductor Li9.42Si1.02P2.1S9.96O2.04 with Li10GeP2S12-type structure in the Li2S–P2S5–SiO2 pseudoternary system: synthesis, electrochemical properties, and structure–composition relationships. Front. Energy Res. 4, 38 (2016).10.3389/fenrg.2016.00038 ↗
54. Vasylenko, A. et al. Element selection for crystalline inorganic solid discovery guided by unsupervised machine learning of experimentally explored chemistry. Nat. Commun. 12, 5561 (2021).10.1038/s41467-021-25343-7 ↗
55. Han, G. et al. Extended condensed ultraphosphate frameworks with monovalent ions combine lithium mobility with high. Comput. Electrochem. Stab. J. Am. Chem. Soc. 143, 18216–18232 (2021).10.1021/jacs.1c07874 ↗
56. Shoko, E. et al. Polymorph of LiAlP2O7: combined computational, synthetic, crystallographic, and ionic conductivity study. Inorg. Chem. 60, 14083–14095 (2021).10.1021/acs.inorgchem.1c01396 ↗