A database of experimentally measured lithium solid electrolyte conductivities evaluated with machine learning

Collapse authors list.
Hargreaves, CJ, Gaultois, MW ORCID: 0000-0003-2172-2507, Daniels, LM ORCID: 0000-0002-7077-6125, Watts, EJ, Kurlin, VA ORCID: 0000-0001-5328-5351, Moran, M, Dang, Y ORCID: 0000-0002-0140-0140, Morris, R, Morscher, A ORCID: 0000-0001-9850-1222, Thompson, K et al (show 22 more authors) , Wright, MA ORCID: 0000-0003-0617-3992, Prasad, BE, Blanc, F ORCID: 0000-0001-9171-1454, Collins, CM ORCID: 0000-0002-0101-4426, Crawford, CA, Duff, BB ORCID: 0000-0002-7398-5002, Evans, J ORCID: 0000-0002-6979-7463, Gamon, J, Han, G ORCID: 0000-0003-3861-5396, Leube, BT, Niu, H, Perez, AJ ORCID: 0000-0003-1659-554X, Robinson, A, Rogan, O, Sharp, PM, Shoko, E, Sonni, M ORCID: 0000-0001-6872-445X, Thomas, WJ, Vasylenko, A ORCID: 0000-0002-6933-0628, Wang, L, Rosseinsky, MJ ORCID: 0000-0002-1910-2483 and Dyer, MS ORCID: 0000-0002-4923-3003 (2023) A database of experimentally measured lithium solid electrolyte conductivities evaluated with machine learning Npj Computational Materials, 9 (1). 9-. ISSN 2057-3960, 2057-3960

Access the full-text of this item by clicking on the Open Access link.

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.

Item Type:	Article
Uncontrolled Keywords:	40 Engineering, 4016 Materials Engineering, 34 Chemical Sciences, 3406 Physical Chemistry, Machine Learning and Artificial Intelligence, Networking and Information Technology R&D (NITRD)
Divisions:	Faculty of Science & Engineering > School of Electrical Engineering, Electronics and Computer Science Faculty of Science & Engineering > School of Physical Sciences
Depositing User:	Symplectic Admin
Date Deposited:	17 Apr 2023 08:42
Last Modified:	01 Mar 2026 11:54
DOI:	10.1038/s41524-022-00951-z
Open Access URL:	https://www.nature.com/articles/s41524-022-00951-z...
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3169593
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.