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

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 degrees C). There are 403 unique chemical compositions with an associated ionic conductivity near room temperature (15-35 degrees 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.

Automated summary

The study presents an expert-curated dataset of lithium ion conductors and their associated conductivities. The dataset contains 820 entries collected from 214 sources, including chemical composition, structural label, and ionic conductivity at specific temperatures. Unsupervised machine learning and the Element Movers Distance were used to analyze the materials in the context of compounds from an inorganic crystal structure database. A CrabNet-based classifier was trained using this dataset to estimate the ionic conductivity of chemical compositions. This classifier serves as a practical tool for experimentalists in prioritizing candidates for further investigation as lithium ion conductors.