Advances in Thermal Modeling and Simulation of Lithium‐Ion Batteries with Machine Learning Approaches

Lithium‐ion batteries (LIBs) are central to modern electric vehicles and energy storage systems, yet heat generation during operation poses risks to performance, aging, and safety. Thus, thermal modeling is essential for reliable battery management. However, traditional approaches for estimating key thermal parameters such as heat capacity, thermal conductivity, and heat generation rate are often inefficient, costly, and poorly suited to dynamic operating conditions. Recently, machine learning (ML) has emerged as a promising tool for improving modeling accuracy and efficiency, enabling data‐driven parameter estimation and temperature prediction. To address the limitations of purely data‐driven models, hybrid approaches that integrate ML with physics‐based frameworks have been developed, offering enhanced accuracy, generalizability, and physical interpretability. This article provides a concise overview of recent progress in ML‐assisted thermal modeling of LIBs and highlights current challenges. With ongoing advances in data quality, model integration, and deployment strategies, ML‐driven thermal models are expected to become key enablers of safe and intelligent battery systems.