Timezone: »

 
Poster
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
Zhihan Gao · Xingjian Shi · Boran Han · Hao Wang · Xiaoyong Jin · Danielle Maddix · Yi Zhu · Mu Li · Yuyang (Bernie) Wang

Wed Dec 13 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #608
in Poster Session 3 »
Event URL: https://github.com/gaozhihan/PreDiff »

Earth system forecasting has traditionally relied on complex physical models that are computationally expensive and require significant domain expertise.In the past decade, the unprecedented increase in spatiotemporal Earth observation data has enabled data-driven forecasting models using deep learning techniques.These models have shown promise for diverse Earth system forecasting tasks but either struggle with handling uncertainty or neglect domain-specific prior knowledge, resulting in averaging possible futures to blurred forecasts or generating physically implausible predictions.To address these limitations, we propose a two-stage pipeline for probabilistic spatiotemporal forecasting: 1) We develop PreDiff, a conditional latent diffusion model capable of probabilistic forecasts. 2) We incorporate an explicit knowledge alignment mechanism to align forecasts with domain-specific physical constraints. This is achieved by estimating the deviation from imposed constraints at each denoising step and adjusting the transition distribution accordingly.We conduct empirical studies on two datasets: N-body MNIST, a synthetic dataset with chaotic behavior, and SEVIR, a real-world precipitation nowcasting dataset. Specifically, we impose the law of conservation of energy in N-body MNIST and anticipated precipitation intensity in SEVIR. Experiments demonstrate the effectiveness of PreDiff in handling uncertainty, incorporating domain-specific prior knowledge, and generating forecasts that exhibit high operational utility.

Author Information

Zhihan Gao (HKUST)
Xingjian Shi (HKUST)
Boran Han (Shell)
Hao Wang (Department of Computer Science, Rutgers University)
Xiaoyong Jin (Amazon)
Danielle Maddix (Amazon Web Services)
Yi Zhu (Boson AI)
Mu Li (Amazon)
Yuyang (Bernie) Wang (AWS AI Labs)

More from the Same Authors