Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression (Papers Track)
Cristian Meo (TUDelft); Varun Sarathchandran (TUDelft); Avijit Majhi (TUDelft); Shao Hung (TUDelft); Carlo Saccardi (TUDelft); Ruben Imhoff (Deltares); Roberto Deidda (University of Cagliari); Remko Uijlenhoet (TUDelft); Justin Dauwels (TUDelft)
Abstract
Predicting precipitation maps is a highly complex spatiotemporal modeling task, critical for mitigating the impacts of extreme weather events. Short-term precipitation forecasting, or nowcasting, requires models that are not only accurate but also computationally efficient for real-time applications. Current methods, such as token-based autoregressive models, often suffer from flawed inductive biases and slow inference, while diffusion models can be computationally intensive. To address these limitations, we introduce BlockGPT, a generative autoregressive transformer using batched tokenization (Block) method that predicts full two-dimensional fields (frames) at each time step. Conceived as a model-agnostic paradigm for video prediction, BlockGPT factorizes space–time by us ing self-attention within each frame and causal attention across frames; in this work, we instantiate it for precipitation nowcasting. We evaluate BlockGPT on two precipitation datasets, viz. KNMI (Netherlands) and SEVIR (U.S.), comparing it to state-of-the-art baselines including token-based (NowcastingGPT) and diffusion-based (DiffCast+Phydnet) models. The results show that BlockGPT achieves superior accuracy, event localization as measured by categorical metrics, and inference speeds up to $31\times$ faster than comparable baselines.