Data refinement for enhanced ionic conductivity prediction in garnet-type solid-state electrolytes

• Published in: Solid state ionics 2024-12, Vol.417, p.116713, Article 116713
• Main Authors: Kharbouch, Zakaria, Bouchaara, Mustapha, Elkouihen, Fadila, Habbal, Abderrahmane, Ratnani, Ahmed, Faik, Abdessamad
• Format: Article
• Language: English
• Subjects: Ionic conductivity prediction; LLZO-type garnet; Machine learning; Solid-state electrolyte
• ISSN: 0167-2738
• DOI: 10.1016/j.ssi.2024.116713

The demand for advanced energy storage drives an urgency to accelerate material discovery in solid-state electrolytes. In pursuit of this aim, this study presents an innovative methodology that integrates materials science insights with machine learning techniques to improve the ionic conductivity prediction in garnet-based solid electrolytes. Utilizing an expanded dataset comprising 362 data points, and exploiting easily obtainable pre-synthesis inputs, our approach incorporates rigorous data preprocessing inspired by materials science and machine learning methodologies. Through systematic feature selection and hyperparameter tuning, the model achieved an improved R-squared value of 0.85. This study highlights the efficacy of the proposed approach and underscores the potential of machine learning in streamlining materials discovery and design for next-generation solid-state batteries. •Improved Ionic Conductivity Prediction: A new approach combining materials science and machine learning for LLZO garnet SSE.•New dataset: Gathered and made available in this study, enriching the predictive modeling for garnet-type solid electrolytes.•Accelerated discovery: Machine learning streamlines materials design, reducing the need for extensive experimental screening.•Practical applicability: Leveraging pre-synthesis features enhances practicality for designing high-conductivity garnet SSE.•Future directions: Expand data, use advanced ML, and integrate theory to enhance model accuracy and generalizability.