Large language models for battery prognostics

Predicting battery health with accuracy and interpretability has become a grand challenge at the intersection of electrochemistry, artificial intelligence, and sustainable energy. Conventional data-driven and physics-based methods remain constrained by nonlinear, coupled, and heterogeneous battery dynamics that limit generalization across chemistries, duty cycles, and environments. Recent breakthroughs in large language models (LLMs) and foundation-model artificial intelligence introduce a paradigm shift—enabling machines to learn from multimodal signals, encode physical laws, and reason adaptively across scales. This review unifies these advances into ten foundational methodologies that delineate the emerging landscape of intelligent battery prognostics: transfer learning, knowledge augmentation, physics-informed and explainable intelligence, ensemble fusion, causal reasoning, continual adaptation, multi-agent coordination, digital-twin coupling, and the pursuit of artificial general intelligence. Together, these dimensions redefine batteries from passive electrochemical devices into cognitive energy systems—self-optimizing, trustworthy, and responsive to uncertainty. Framed within the broader evolution toward Industry 5.0, we chart a roadmap for autonomous battery management that fuses physics, data, and reasoning, establishing artificial intelligence as a scientific and technological cornerstone for the next generation of resilient, adaptive, and sustainable electrification.