Liangxi He
Papers
1
Total Citations
3
H-Index
1
About
Liangxi He is a researcher at the forefront of explainable artificial intelligence for energy storage systems, with a primary focus on battery aging and degradation mechanisms. His most notable contribution is the development of MELODI, an explainable machine learning method designed to mechanistically disentangle battery calendar aging. This work, published in 2025, provides a novel framework that moves beyond black-box predictions, enabling researchers to interpret the underlying physical and chemical processes driving capacity fade over time. By integrating domain knowledge with interpretable models, He’s approach offers a powerful tool for accelerating battery lifespan optimization and materials discovery. Although early in its citation trajectory, MELODI has already garnered 3 citations, signaling growing interest from the battery and machine learning communities. He’s research bridges critical gaps between data-driven modeling and mechanistic understanding, making his work particularly valuable for students and researchers seeking to apply AI in electrochemistry. His contributions are poised to influence next-generation battery diagnostics and sustainable energy storage solutions.
Research Focus
Key Achievements
Top Papers
- 1