Advanced Battery State Monitoring in Electric Vehicles: A Comprehensive Review of Spatiotemporal Dynamics and Federated Learning Approaches

With the global proliferation of electric vehicles, battery state monitoring has emerged as a foundation for ensuring operational safety and reliability. However, in real-world applications, battery systems operate within complex dynamic spatiotemporal contexts, characterized by non-stationary aging drift in the temporal dimension and cross-scale heterogeneity in the spatial dimension. While existing reviews extensively cover specific parameter estimation, most studies rely on static assumptions or isolated technical paths, failing to capture the deep spatiotemporal coupling mechanisms or meet the privacy and bandwidth constraints of distributed vehicular environments. To bridge this gap, this article provides a comprehensive review of battery monitoring algorithms, organized by temporal, spatial, and spatiotemporal dimensions. Furthermore, to address the limitations of centralized paradigms in managing heterogeneous data, we analyze a decoupling-interaction framework enabled by federated learning. By shifting the monitoring paradigm toward cloud-edge collaborative intelligence, this framework facilitates localized spatiotemporal decoupling for heterogeneous data adaptation and cloud-based interaction for global evolutionary pattern mining. Finally, we offer insights into the open challenges of practical deployment, and further discuss the transition of monitoring algorithms toward semantic reasoning via foundation models, physics-constrained communication, and generative continual learning. This provides a systematic research perspective and future direction for battery state monitoring within dynamic spatiotemporal contexts.