Machine Learning Enabled Prediction of Cathode Materials for Zn ion Batteries

TL;DR

This paper presents a machine learning approach that screens a large database of inorganic materials to identify promising cathode candidates for Zn-ion batteries, aiming to accelerate materials discovery.

Contribution

It introduces a combined ML method using CGCNN and AFLOW data to predict high-capacity, high-voltage cathodes, enabling efficient screening of thousands of materials.

Findings

Successfully screened over 130,000 materials for potential cathodes.

Predicted new promising cathode candidates for Zn-ion batteries.

Validated the ML approach with experimental data alignment.

Abstract

Rechargeable Zn batteries with aqueous electrolytes have been considered as promising alternative energy storage technology, with various advantages such as low cost, high volumetric capacity, environmentally friendly, and high safety. However, a lack of reliable cathode materials has largely pledged their applications. Herein, we developed a machine learning (ML) based approach to predict cathodes with high capacity (>150 mAh/g) and high voltage (>0.5V). We screened over ~130,000 inorganic materials from the Materials Project database and applied the crystal graph convolutional neural network (CGCNN) based ML approach with data from the AFLOW database. The combination of these two could not only screen cathode materials that match well with the experimental data but also predict new promising candidates for further experimental validations. We hope this study could spur further interests in ML-based advanced theoretical tools for battery materials discovery.