Publications

Data-Driven Discovery of Lithium–Sulfur Catalysts via Two-Stage Large Language Model Fine-Tuning and Mechanistic Validation

Published in Materials Today Energy, 2026

A fully automated, literature-driven framework integrating paper-aware information extraction, domain-specific language-model fine-tuning, multidimensional catalyst evaluation, external consistency assessment, and mechanistic validation for lithium–sulfur battery catalyst screening. Its modular architecture is designed to support adaptation to other materials-discovery tasks through domain-specific data, evaluation criteria, and validation modules.

Recommended citation: Liu, H.; Li, S.; Huang, Y.; Zhao, Z.; Wu, G.; Wang, N.; Sun, Z.; Liu, C.; Yan, H.; Wu, Z.; Wang, Z.; Liu, E.; Shan, Z.; Shi, C.; He, F.; He, C.; Zhao, N.; Tang, Y.; Hu, Y.; Chen, B. (2026). "Data-Driven Discovery of Lithium–Sulfur Catalysts via Two-Stage Large Language Model Fine-Tuning and Mechanistic Validation." Materials Today Energy 59, 102371.
Download Paper

How Machine Learning Has Driven the Development of Rechargeable Ion Batteries

Published in Advanced Energy Materials, 2025

This review examines machine-learning workflows for rechargeable battery research, including data acquisition, preprocessing, model development, interpretability, applications across battery chemistries, and emerging closed-loop research paradigms.

Recommended citation: Liu, H.; Li, S.; Zhu, S.; Hu, Y.; Han, X.; Shi, C.; He, F.; He, C.; Chen, B.; Zhao, N. (2025). "How Machine Learning Has Driven the Development of Rechargeable Ion Batteries." Advanced Energy Materials 15, e04095.
Download Paper

Advanced hard carbon materials for practical applications of sodium-ion batteries developed by combined experimental, computational, and data analysis approaches

Published in Progress in Materials Science, 2025

This study establishes a literature-data-driven framework for the analysis and design of hard-carbon anodes for sodium-ion batteries. A custom data-collection and processing pipeline was used to curate precursor, synthesis, structural, and electrochemical information from published studies, followed by missing-data imputation and machine-learning modelling. Random Forest and SHAP analyses were employed to identify and interpret relationships between preparation parameters, microstructural characteristics, initial Coulombic efficiency, and reversible capacity. The resulting workflow provides data-informed insights for hard-carbon optimization and a transferable foundation for broader energy-materials research.

Recommended citation: Sun, Z.; Liu, H.; Li, W.; Zhang, N.; Zhu, S.; Chen, B.; He, F.; Zhao, N.; He, C. (2025). "Advanced hard carbon materials for practical applications of sodium-ion batteries developed by combined experimental, computational, and data analysis approaches." Progress in Materials Science 149, 101401.
Download Paper

Descriptor-based Machine Learning for Coordination-Engineered Single-Atom Catalysts

Ongoing research, 2026

This work establishes a systematic ML pipeline to extract reliable material design rules from noisy, high-dimensional experimental datasets. By distilling 376,000+ dynamic cycling records into robust performance metrics and implementing symmetry-aware “Rotation Augmentation,” the framework addresses the challenges associated with small-sample laboratory data. The project bridges the gap between raw electrochemical curves and actionable catalyst screening. This data-driven strategy is designed to be transferable to other conversion-type battery systems and to accelerate the discovery of high-retention catalysts.