Selection of solid-state electrolytes for lithium-ion batteries using clustering technique

Abstract

In the context of solid-state electrolytes for batteries, ambient temperature ionic conductivity stands as a pivotal attribute. This investigation presents a compilation of potential candidates for solid-state electrolytes in lithium-ion batteries, employing clustering—an unsupervised machine-learning technique. To achieve this, a fusion of data from two distinct datasets was undertaken: a smaller dataset consisting of 51 compounds endowed with experimental lithium-ion conductivity data and a substantially larger dataset of 15,530 compounds devoid of such information. The compounds in our dataset were divided into various groups based on several characteristics that influence the conductivity of lithium-ion batteries. Then, the location of the compounds known to have high lithium-ion conductivity (>10⁻⁴ S cm⁻¹) at room temperature was observed. The 427 compounds (i.e., unique material project IDs) found in the same cluster as most of these high-conducting compounds are then further examined. This paper concludes by offering a catalog of solid-state compounds that can be utilized to choose compounds for solid-state electrolytes in batteries.

Graphical Abstract

Synopsis: The above plot shows the 15530 lithium-based compounds clustered into 7 clusters based on several factors that were identified to affect lithium-ion conductivity. We observe the location of the already known good lithium-ion conductors (represented by the golden stars) to identify other similar compounds.