Fine-Tuning Universal Machine Learning Potentials Enables Efficient Computation of Li Electrode Potentials in Battery Electrolytes
Journal of the American Chemical Society · 11.11.2026 · 148 (44) · 47908-47919
DOI: 10.1021/jacs.6c12519 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Chemical Society, online erschienen am 30.10.2026. Verfasst von Feng Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Physical Chemistry of Solid Surfaces, iChEM, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen361005, …. Die Arbeit nennt 112 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministry of Education of the People's Republic of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
The electrode potential of Li metal is fundamental to the performance and stability of Li-metal batteries, yet its accurate prediction across diverse electrolyte chemistries remains a challenge. Standard quantum chemistry using cluster models fails to account for explicit bulk solvation, while ab initio molecular dynamics is restricted by the high computational cost of thermodynamic sampling. In this work, we present an integrated framework that combines a universal machine learning potential for electrolytes with a data-efficient fine-tuning strategy to compute Li electrode potentials. This workflow achieves ab initio level accuracy using ∼200 extra density functional theory calculations per electrolyte system. Furthermore, the identified relationship between local Li+ solvation environments and electrode potential shifts provides mechanistic insights into electrolyte-dependent redox behavior and offers guidance for rational electrolyte design.
Autor:innen und Institutionen
- State Key Laboratory of Physical Chemistry of Solid Surfaces, iChEM, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen361005, China.
- Laboratory of AI for Electrochemistry (AI4EC), Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM), Xiamen361005, China.
- CATL 21C Innovation Laboratory, Contemporary Amperex Technology Ltd., Ningde352100, China.
- Institute of Artificial Intelligence, Xiamen University, Xiamen361005, China.
ORCID-Profile: Jun Cheng
Förderung
- National Natural Science Foundation of China
- Ministry of Education of the People's Republic of China
- Fundamental Research Funds for the Central Universities
- National Science and Technology Major Project
Zitieren
APA
Wang, F., Tang, Y. H., Wei, Y. M., & Cheng, J. (2026). Fine-Tuning Universal Machine Learning Potentials Enables Efficient Computation of Li Electrode Potentials in Battery Electrolytes. Journal of the American Chemical Society, 148(44), 47908-47919. https://doi.org/10.1021/jacs.6c12519
Vancouver
Wang F, Tang YH, Wei YM, Cheng J. Fine-Tuning Universal Machine Learning Potentials Enables Efficient Computation of Li Electrode Potentials in Battery Electrolytes. Journal of the American Chemical Society. 2026;148(44):47908-47919. doi:10.1021/jacs.6c12519
BibTeX
@article{Wang2026,
author = {Wang, Feng and Tang, Yu-Hang and Wei, Yi-Min and Cheng, Jun},
title = {Fine-Tuning Universal Machine Learning Potentials Enables Efficient Computation of Li Electrode Potentials in Battery Electrolytes},
journal = {Journal of the American Chemical Society},
year = {2026},
volume = {148},
number = {44},
pages = {47908--47919},
doi = {10.1021/jacs.6c12519}
}
EUVIMED