Machine Learning–Driven Development of Highly Dense Ga-LLZO Solid Electrolyte Pellet Published in Elsevier Journal

 

I’m happy to share that my recent research article titled

“Development of Highly Dense Solid Electrolyte Pellet Using a Machine Learning Approach”
has been published in Solid State Communications (Elsevier).

Research Paper DOI: https://doi.org/10.1016/j.ssc.2025.116038

---

Overview of the Research

This work demonstrates how machine learning can support materials optimization and help resolve several challenges in battery research. While machine learning has been widely applied in battery performance prediction, its use in materials-level optimization for solid-state batteries is still emerging.

Our study focuses specifically on overcoming the sinterability issues of Ga-doped LLZO solid electrolyte pellets, which is one of the major bottlenecks in the fabrication of high-density, high-performance all-solid-state lithium batteries.

---

Why This Research Matters

Solid-state batteries face multiple challenges, including:

• Low ionic conductivity

• High interfacial resistance

• Poor densification of solid electrolytes

• Dendrite formation

• Mechanical instability

This publication focuses mainly on the densification optimization of LLZO pellets, which directly impacts ionic transport and overall battery performance.