{"ID":2859300,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.06293","arxiv_id":"2510.06293","title":"BlockGPT: Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression","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 using 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 31x faster than comparable baselines.","short_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, s...","url_abs":"https://arxiv.org/abs/2510.06293","url_pdf":"https://arxiv.org/pdf/2510.06293v2","authors":"[\"Cristian Meo\",\"Varun Sarathchandran\",\"Avijit Majhi\",\"Shao Hung\",\"Carlo Saccardi\",\"Ruben Imhoff\",\"Roberto Deidda\",\"Remko Uijlenhoet\",\"Justin Dauwels\"]","published":"2025-10-07T11:52:32Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}