Artificial Intelligence Facilitates Electrolyte Screening for High-Performance Batteries

Research from the Taiyuan University of Technology has led to a breakthrough in the development of high-performance batteries using artificial intelligence. The study focuses on the electrolyte screening process, which is a critical component in achieving optimal battery performance. According to the research, artificial intelligence facilitates electrolyte screening by correlating the complex physicochemical properties of solvent/clusters with battery performance. However, traditional static models struggle to model and interpret the high-dimensional relationships between the dynamic evolution of ion-solvent clusters and their electrochemical performance.

Key Takeaways:

• The research developed a dynamic solvation model by precisely extracting descriptors of the composition, solvation, and migration stages for solvated ions.
• The model revealed that the optimal anion-coordinated solvation structure for rechargeable magnesium batteries (RMBs) features ligand coordination numbers (CNs) of 2/3/4 and an atomic CN of 5, enhancing desolvation and solid electrolyte interphase formation.
• The diffusion coefficient, crucial for ionic conductivity, is influenced by dielectric constants and solvent properties.
• The intelligent screening process based on the model identifies electrolytes that demonstrate a low overpotential and long cycle life in experimental validation.
• The research has been peer-reviewed and has been published in the journal Energy & Environmental Science.
• The study was supported by the National Natural Science Foundation of China (NSFC) and the Special Fund for Science and Technology Innovation Team of Shanxi Province.
• The research team includes Zhijun Zuo, Ruimin Li, Wanyu Zhao, Zhengqing Fan, Meng Zhang, Jiayi Li, Rushuai Li, and Xiaowei Yang from the Taiyuan University of Technology.

Statistics:

• 2/3/4: the optimal ligand coordination numbers (CNs) for the anion-coordinated solvation structure of RMBs.
• 5: the optimal atomic CN for the anion-coordinated solvation structure of RMBs.
• 10: the number of researchers involved in the study.
• 2025: the year in which the research was published.

Sources:

• Data-driven Design of Advanced Magnesium-battery Electrolyte via Dynamic Solvation Models. Energy & Environmental Science, 2025.
• NewsRx. Taiyuan University of Technology Reports Findings in Artificial Intelligence (Data-driven Design of Advanced Magnesium-battery Electrolyte via Dynamic Solvation Models). Information Technology Newsweekly. July 1, 2025; p 800.