Collaborative Deterministic-Probabilistic Forecasting for Diverse Spatiotemporal Systems
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_ | 1866914059721375744 |
|---|---|
| author | Sheng, Zhi Yuan, Yuan Zhang, Yudi Ding, Jingtao Li, Yong |
| author_facet | Sheng, Zhi Yuan, Yuan Zhang, Yudi Ding, Jingtao Li, Yong |
| contents | Probabilistic forecasting is crucial for real-world spatiotemporal systems, such as climate, energy, and urban environments, where quantifying uncertainty is essential for informed, risk-aware decision-making. While diffusion models have shown promise in capturing complex data distributions, their application to spatiotemporal forecasting remains limited due to complex spatiotemporal dynamics and high computational demands. we propose CoST, a general forecasting framework that collaborates deterministic and diffusion models for diverse spatiotemporal systems. CoST formulates a mean-residual decomposition strategy: it leverages a powerful deterministic model to capture the conditional mean and a lightweight diffusion model to learn residual uncertainties. This collaborative formulation simplifies learning objectives, improves accuracy and efficiency, and generalizes across diverse spatiotemporal systems. To address spatial heterogeneity, we further design a scale-aware diffusion mechanism to guide the diffusion process. Extensive experiments across ten real-world datasets from climate, energy, communication, and urban systems show that CoST achieves 25\% performance gains over state-of-the-art baselines, while significantly reducing computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11013 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Collaborative Deterministic-Probabilistic Forecasting for Diverse Spatiotemporal Systems Sheng, Zhi Yuan, Yuan Zhang, Yudi Ding, Jingtao Li, Yong Machine Learning Artificial Intelligence Probabilistic forecasting is crucial for real-world spatiotemporal systems, such as climate, energy, and urban environments, where quantifying uncertainty is essential for informed, risk-aware decision-making. While diffusion models have shown promise in capturing complex data distributions, their application to spatiotemporal forecasting remains limited due to complex spatiotemporal dynamics and high computational demands. we propose CoST, a general forecasting framework that collaborates deterministic and diffusion models for diverse spatiotemporal systems. CoST formulates a mean-residual decomposition strategy: it leverages a powerful deterministic model to capture the conditional mean and a lightweight diffusion model to learn residual uncertainties. This collaborative formulation simplifies learning objectives, improves accuracy and efficiency, and generalizes across diverse spatiotemporal systems. To address spatial heterogeneity, we further design a scale-aware diffusion mechanism to guide the diffusion process. Extensive experiments across ten real-world datasets from climate, energy, communication, and urban systems show that CoST achieves 25\% performance gains over state-of-the-art baselines, while significantly reducing computational cost. |
| title | Collaborative Deterministic-Probabilistic Forecasting for Diverse Spatiotemporal Systems |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.11013 |