Return
Data-Driven Composition-Only Machine Learning for High-Performance Solid-State Electrolytes
DOI:10.1039/D5QM00438A.png)
Abstract
En 中文
As a pivotal advancement in energy storage technology; all-solid-state batteries represent a transformative direction for next-generation lithium-ion batteries. To address the critical challenge of low ionic conductivity in solid-state electrolytes (SSEs); we propose a machine learning driven screening workflow to search for SSE with high ionic conductivity. Leveraging an experimentally database of lithium-ion SSEs; we train five ensemble boosting models using exclusively elemental composition and temperature parameters. The CatBoost algorithm emerges as the optimal predictor; achieving superior accuracy in ionic conductivity estimation. Implementing this model; we systematically screen 3; 311 lithium-containing materials from the Materials Project database; identifying 22 promising candidates with predicted ionic conductivity exceeding 1 mS/cm. Especially; the predicted conductivity of Li8SeN2 (2.72 mS/cm) is well consistent with the AIMD measurement (2.85 mS/cm). This data-driven approach accelerates SSE discovery while providing fundamental insights into structure-property relationships; establishing a robust framework for next-generation electrolyte development.
Keywords:
all-solid-state batteries
solid-state electrolytes
ionic conductivity
machine learning
materials screening
Journal
IF:
6.4
Papers:
3.2K
Citations:
1.5W
Organization
No organization information available
Cited Papers
Mechanochemical synthesis of Li-argyrodite Li6PS5X (X = Cl, Br, I) as sulfur-based solid electrolytes for all solid state batteries application
SOLID STATE IONICS
IF3.3
Effects of Different Doping Strategies on Cubic Li7La3Zr2O12 Solid-State Li-Ion Battery Electrolytes
Computation-Accelerated Design of Materials and Interfaces for All-Solid-State Lithium-Ion Batteries
JOULE
IF35.4

