BlockGPT: Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914108129935360 |
|---|---|
| author | Meo, Cristian Sarathchandran, Varun Majhi, Avijit Hung, Shao Saccardi, Carlo Imhoff, Ruben Deidda, Roberto Uijlenhoet, Remko Dauwels, Justin |
| author_facet | Meo, Cristian Sarathchandran, Varun Majhi, Avijit Hung, Shao Saccardi, Carlo Imhoff, Ruben Deidda, Roberto Uijlenhoet, Remko Dauwels, Justin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BlockGPT: Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression Meo, Cristian Sarathchandran, Varun Majhi, Avijit Hung, Shao Saccardi, Carlo Imhoff, Ruben Deidda, Roberto Uijlenhoet, Remko Dauwels, Justin Machine Learning Artificial Intelligence 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. |
| title | BlockGPT: Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.06293 |