Two-Stage Rainfall-Forecasting Diffusion Model

Xudong Ling

doi:10.1109/LGRS.2024.3382241

Return

Two-Stage Rainfall-Forecasting Diffusion Model

2024-01-01

DOI：10.1109/LGRS.2024.3382241

Original

Original request for help

Save

Abstract

En 中文

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 the state-of-the-art results on the MRMS and Swedish radar datasets. On the Swedish dataset, our proposed method achieves a 5%-10%-point improvement in CSI compared to the other baseline methods for the 60-80 min prediction range. Our project is open source and available on GitHub at: https://github.com/clearlyzerolxd/TRDM.

Keywords:

Rain

Predictive models

Training

Image reconstruction

Spatial resolution

Computational modeling

Superresolution

Diffusion model

Generative adversarial networks (GANs)

rainfall prediction