My research develops physics-informed and interpretable machine learning methods for complex physical systems, with a focus on electrochemical energy storage. I establish a methodological framework that integrates electrochemical modeling with data-driven approaches to enable reliable, transferable, and interpretable prediction and control under real-world uncertainty and limited data. My work bridges model based scientific understanding and machine learning, contributing to the development of next-generation data-driven modeling paradigms with applications in battery diagnostics, aging analysis, and digital twins.