From Composition to Ionic Conductivity: Machine Learning‐Guided Discovery and Experimental Validation of Argyrodite‐Type Lithium‐Ion Electrolytes (Small 2/2026)

Small 2026 Open access

Read full text
Authors: Songjia Kong, Ziheng Yu, Naoki Matsui, Michiyo Kamiya, Yudai Iwamizu, Yuki Tanaka, Nobuko Kubota, K. Nomoto, Satoshi Hori, Masaaki Hirayama, Kota Suzuki, Ryoji Kanno
DOI: 10.1002/smll.71850
Cited by: 0

Abstract

Lithium-Ion Electrolytes The cover illustrates the composition-based machine learning framework Elements-To-Ionics (E2I) for predicting and optimizing ionic conductivities of argyrodite-type solid-state electrolytes. Guided by E2I predictions, in article number 2509918, Kota Suzuki, Ryoji Kanno, and co-workers successfully explored Si–Sn, Ge–Si, and Ge–Sn co-doped Li6PS5I systems, achieving ionic conductivities comparable to superionic conductors. This work highlights the potential of composition-based informatics for accelerating next-generation solid-state battery development.

Fields of Study & Subjects

Machine Learning in Materials Science Advanced Battery Materials and Technologies Inorganic Chemistry and Materials

Publication details

Journal / source
Small
Volume
22
Issue
2
Publication date
1 January 2026
Language
EN