Universal Battery Capacity Degradation Forecasting Driven by Foundation Models Across Diverse Chemistries and Conditions.

Accurate forecasting of battery capacity fade is essential for the safety, reliability, and long-term efficiency of energy storage systems. However, the heterogeneity across cell chemistries, form factors, and operating conditions makes it difficult to build a single model that generalizes beyond its training domain. This work proposes a unified capacity forecasting framework that maintains robust performance across diverse chemistries and usage scenarios. We curate 20 public aging datasets into a large-scale corpus covering 1704 cells and 3 961 195 charge-discharge cycle segments, spanning temperatures from - 5 ∘ C to 45 ∘ C , multiple C-rates, and application-oriented profiles such as fast charging and partial cycling. On this corpus, we adopt a Time-Series Foundation Model (TSFM) backbone and apply parameter-efficient Low-Rank Adaptation (LoRA) together with physics-guided contrastive representation learning to capture shared degradation patterns. Experiments on both "known" and held-out "unknown" datasets show that a single unified model achieves competitive or superior accuracy compared with recent state-of-the-art time-series forecasting methods trained separately for each dataset, while retaining stable performance on chemistries, capacity scales, and operating conditions excluded from training. These results demonstrate the potential of TSFM-based architectures as a scalable and transferable solution for capacity degradation forecasting in battery management systems.