STLDM: Spatio-Temporal Latent Diffusion Model for Precipitation Nowcasting

TMLR Paper5706 Authors

Abstract: Precipitation nowcasting is a critical spatio-temporal prediction task for society to prevent severe damage owing to extreme weather events. Despite the advances in this field, the complex and stochastic nature of this task still poses challenges to existing approaches. Specifically, deterministic models tend to produce blurry predictions while generative mod- els often struggle with poor accuracy. In this paper, we present a simple yet effective model architecture termed STLDM, which learns the latent representation from end to end along- side both the Variational Autoencoder and the conditioning network. Experimental results on multiple radar datasets demonstrate that STLDM achieves superior performance com- pared to the state of the art, while also improving inference efficiency.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Andreas_Lehrmann1

Submission Number: 5706