Two-stage Rainfall-Forecasting Diffusion Model
This work addresses rainfall prediction for meteorology and climate science, but it appears incremental as it builds on existing diffusion models for a specific domain.
The paper tackles the problem of blurry images and incorrect spatial positions in rainfall forecasting by proposing a two-stage diffusion model (TRDM) that improves long-term accuracy and balances temporal and spatial modeling, achieving state-of-the-art results on MRMS and Swedish radar datasets.
Deep neural networks have made great achievements in rainfall prediction.However, the current forecasting methods have certain limitations, such as with blurry generated images and incorrect spatial positions. To overcome these challenges, we propose a Two-stage Rainfall-Forecasting Diffusion Model (TRDM) aimed at improving the accuracy of long-term rainfall forecasts and addressing the imbalance in performance between temporal and spatial modeling. TRDM is a two-stage method for rainfall prediction tasks. The task of the first stage is to capture robust temporal information while preserving spatial information under low-resolution conditions. The task of the second stage is to reconstruct the low-resolution images generated in the first stage into high-resolution images. We demonstrate state-of-the-art results on the MRMS and Swedish radar datasets. Our project is open source and available on GitHub at: \href{https://github.com/clearlyzerolxd/TRDM}{https://github.com/clearlyzerolxd/TRDM}.