ClimateAR: Multi-Scale Autoregressive Generative Modeling for Climate Forecasting

Yue Yu, Weiqi Chen, Binqing Wu, Wanyi Jiang, Dongliang Cui, Zongjiang Shang, Bo Wu, Liang Sun, Ling Chen

Keywords: Weather and climate forecasting

Abstract: Accurate Seasonal‑to‑interannual climate forecasting provides critical support for decision-making in agriculture, energy, and disaster preparedness. Current deterministic models often fail to capture climate uncertainty, while existing generative approaches oversimplify the system by neglecting key spatiotemporal dependencies and cross-scale interactions. To address these limitations, we introduce **ClimateAR**, an AutoRegressive generative model for probabilistic Climate forecasting. The framework incorporates two novel components: (1) an aligned tokenizer that bridges and aligns heterogeneous simulation and real-world data to improve transferability across domains, and (2) a mixed-scale conditioning mechanism that captures multi-scale climate interactions for robust probabilistic forecasting. Extensive evaluations on the ERA5 reanalysis dataset show that ClimateAR achieves state-of-the-art performance, improving anomaly correlation skill by 29.27\% on average compared to leading baselines. Code is available at https://anonymous.4open.science/r/ClimateAR-956D.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 11323