With the rapid deployment of renewable energy and battery energy storage systems (BESS), reliable battery diagnostics are essential for ensuring safety, performance, and long service life. This PhD project will develop next-generation diagnostic and prognostic tools by combining physics-based electrochemical models with machine learning for accurate estimation of battery state, health, and degradation. The research will involve computational model development, data-driven algorithms, and validation using experimental battery data, with applications in grid-scale energy storage, electric vehicles, and renewable energy integration. The project offers interdisciplinary training at the interface of electrochemical engineering, mathematical modeling, artificial intelligence, and energy systems.