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.

Details

Title
A database of experimentally measured lithium solid electrolyte conductivities evaluated with machine learning
Author
Hargreaves, Cameron J. 1 ; Gaultois, Michael W. 2 ; Daniels, Luke M. 1 ; Watts, Emma J. 2 ; Kurlin, Vitaliy A. 3 ; Moran, Michael 2 ; Dang, Yun 1 ; Morris, Rhun 1 ; Morscher, Alexandra 1 ; Thompson, Kate 1 ; Wright, Matthew A. 1   VIAFID ORCID Logo  ; Prasad, Beluvalli-Eshwarappa 1 ; Blanc, Frédéric 4 ; Collins, Chris M. 1 ; Crawford, Catriona A. 1 ; Duff, Benjamin B. 5 ; Evans, Jae 1   VIAFID ORCID Logo  ; Gamon, Jacinthe 1 ; Han, Guopeng 1 ; Leube, Bernhard T. 1 ; Niu, Hongjun 1 ; Perez, Arnaud J. 1   VIAFID ORCID Logo  ; Robinson, Aris 1 ; Rogan, Oliver 2 ; Sharp, Paul M. 1 ; Shoko, Elvis 1 ; Sonni, Manel 1 ; Thomas, William J. 1 ; Vasylenko, Andrij 1   VIAFID ORCID Logo  ; Wang, Lu 1 ; Rosseinsky, Matthew J. 2 ; Dyer, Matthew S. 2   VIAFID ORCID Logo 

1  University of Liverpool, Department of Chemistry, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470) 
2  University of Liverpool, Department of Chemistry, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470); University of Liverpool, Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470) 
3  University of Liverpool, Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470); University of Liverpool, Department of Computer Science, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470) 
4  University of Liverpool, Department of Chemistry, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470); University of Liverpool, Leverhulme Research Centre for Functional Materials Design, Materials Innovation Factory, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470); University of Liverpool, Stephenson Institute for Renewable Energy, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470) 
5  University of Liverpool, Department of Chemistry, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470); University of Liverpool, Stephenson Institute for Renewable Energy, Liverpool, UK (GRID:grid.10025.36) (ISNI:0000 0004 1936 8470) 
Pages
9
Publication year
2023
Publication date
2023
Publisher
Nature Publishing Group
e-ISSN
20573960
Source type
Scholarly Journal
Language of publication
English
DOI
https://doi.org/10.1038/s41524-022-00951-z
ProQuest document ID
2765887693
Copyright
© The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.